[{"data":1,"prerenderedAt":2247},["ShallowReactive",2],{"blog-post-nl-\u002Fblog\u002Fpaiton-qwen38-flash-next-4bit-radeon-ai-pro-r9700":3,"blog-posts-sidebar-nl":1729},{"id":4,"title":5,"body":6,"categories":1710,"date":1715,"description":1716,"extension":1717,"heading":1718,"image":1719,"meta":1720,"navigation":973,"originalUrl":1721,"path":1722,"seo":1723,"slug":1724,"socialImage":1725,"stem":1726,"updated":1727,"__hash__":1728},"blogNl\u002Fblog\u002Fpaiton-qwen38-flash-next-4bit-radeon-ai-pro-r9700.md","Qwen3.8 Flash Next in 4-bit op 2 × Radeon R9700: getest tegenover 16-bit",{"type":7,"value":8,"toc":1695},"minimark",[9,34,57,65,70,84,88,94,162,171,188,193,202,205,210,286,295,345,366,387,396,400,413,416,421,459,484,488,509,512,521,583,634,655,659,678,681,686,733,756,789,793,814,827,838,855,872,876,914,923,1165,1195,1216,1219,1285,1301,1305,1319,1344,1348,1355,1359,1372,1391,1691],[10,11,12,13,17,18,21,22],"p",{},"Het 16-bit checkpoint van Qwen3.8 Flash Next is ",[14,15,16],"strong",{},"360 GB",". Twee Radeon AI PRO R9700-kaarten hebben samen 64 GB VRAM, dus het originele model past daar bij lange na niet op. Onze nieuwe ",[14,19,20],{},"4-bit release draait op die twee kaarten",", met resultaten dicht bij de 16-bit referentie op rekenen, Python-code en kennistaken.",[23,24,25],"sup",{},[26,27,33],"a",{"href":28,"ariaDescribedBy":29,"dataFootnoteRef":31,"id":32},"#user-content-fn-model",[30],"footnote-label","","user-content-fnref-model","1",[10,35,36,37,40,41,44,45,48,49],{},"Het praktische resultaat: ",[14,38,39],{},"189,8 tokens\u002Fs voor gewogen generatie met één verzoek",", ",[14,42,43],{},"420,7 tokens\u002Fs bij acht gelijktijdige verzoeken",", en een optionele RAM-prefixcache voor lange codegesprekken. Het blijft gewone vLLM met de Paiton-plugin en onze eigen kernels. De gemeten opstelling vraagt een ",[14,46,47],{},"host met 256 GB RAM",", omdat minder gebruikte experts en grote tabellen in systeemgeheugen staan.",[23,50,51],{},[26,52,56],{"href":53,"ariaDescribedBy":54,"dataFootnoteRef":31,"id":55},"#user-content-fn-fourbit",[30],"user-content-fnref-fourbit","2",[10,58,59,60,64],{},"Dit volgt op onze ",[26,61,63],{"href":62},"\u002Fnl\u002Fblog\u002Fpaiton-qwen38-flash-next-radeon-ai-pro-r9700","3-bit Flash Next-release",". Hier ligt de prioriteit bij het behouden van meer van de kwaliteit van het oorspronkelijke model.",[66,67,69],"h2",{"id":68},"nauwkeurigheid-tegenover-het-16-bit-model","Nauwkeurigheid tegenover het 16-bit model",[10,71,72,73,77,78],{},"We lieten beide modellen dezelfde vragen beantwoorden, met dezelfde prompts, samplingseeds per vraag en chattemplate met thinking aan. Het 4-bit model gebruikte de uitgebrachte serving-modus ",[74,75,76],"code",{},"4bit","; de 16-bit referentie gebruikte het originele checkpoint.",[23,79,80],{},[26,81,33],{"href":28,"ariaDescribedBy":82,"dataFootnoteRef":31,"id":83},[30],"user-content-fnref-model-2",[85,86],"flash-next-four-bit-figure",{"kind":87},"accuracy",[10,89,90],{},[91,92,93],"em",{},"Taaknauwkeurigheid; hoger is beter. GSM8K en HumanEval gebruiken hun volledige testsets. MMLU-Pro gebruikt een vaste subset van 1.400 vragen, 100 per categorie voor alle 14 categorieën. HumanEval is pass@1. Beide modellen hebben een antwoordlimiet van 16.384 tokens.",[95,96,97,117],"table",{},[98,99,100],"thead",{},[101,102,103,107,111,114],"tr",{},[104,105,106],"th",{},"Taak",[104,108,110],{"align":109},"right","Vragen",[104,112,113],{"align":109},"16-bit",[104,115,116],{"align":109},"Paiton 4-bit",[118,119,120,135,148],"tbody",{},[101,121,122,126,129,132],{},[123,124,125],"td",{},"GSM8K, rekenen",[123,127,128],{"align":109},"1.319",[123,130,131],{"align":109},"96,9%",[123,133,134],{"align":109},"96,8%",[101,136,137,140,143,146],{},[123,138,139],{},"HumanEval, Python-code",[123,141,142],{"align":109},"164",[123,144,145],{"align":109},"96,3%",[123,147,145],{"align":109},[101,149,150,153,156,159],{},[123,151,152],{},"MMLU-Pro, kennis",[123,154,155],{"align":109},"1.400",[123,157,158],{"align":109},"84,7%",[123,160,161],{"align":109},"83,7%",[10,163,164,165],{},"GSM8K verschilt met 0,1 procentpunt; HumanEval is gelijk. Met een tweede reeks seeds veranderde het 16-bit model zelf met 0,0 punten op GSM8K en 1,2 punten op HumanEval. De gepaarde toetsen voor beide gekwantiseerde vergelijkingen geven p = 1,00.",[23,166,167],{},[26,168,33],{"href":28,"ariaDescribedBy":169,"dataFootnoteRef":31,"id":170},[30],"user-content-fnref-model-3",[10,172,173,174,177,178,181,182],{},"MMLU-Pro ligt één punt lager voor het 4-bit model, met een gepaard 95%-interval van ",[14,175,176],{},"−2,3 tot +0,3 punten"," en p = 0,16. Dat bewijst geen statistische gelijkwaardigheid. Meer 4-bit antwoorden bereikten de antwoordlimiet: 104 tegenover 79. Op de ",[14,179,180],{},"1.271 vragen waarbij geen van beide modellen die limiet bereikte",", zijn de scores 91,1% voor 4-bit en 91,0% voor 16-bit. Die subset helpt het verschil te beschrijven, maar bewijst niet dat een langere limiet het zou wegnemen.",[23,183,184],{},[26,185,33],{"href":28,"ariaDescribedBy":186,"dataFootnoteRef":31,"id":187},[30],"user-content-fnref-model-4",[189,190,192],"h3",{"id":191},"meer-dan-alleen-taakscores","Meer dan alleen taakscores",[10,194,195,196],{},"Taakscores kunnen verschillen in tokenvoorspellingen verbergen. Daarom maten we ook perplexiteit, negatieve log-likelihood bij lange documenten en KL-divergentie over de volledige woordenschat tegenover BF16, de 16-bit referentie.",[23,197,198],{},[26,199,33],{"href":28,"ariaDescribedBy":200,"dataFootnoteRef":31,"id":201},[30],"user-content-fnref-model-5",[85,203],{"kind":204},"quality",[10,206,207],{},[91,208,209],{},"Toename in perplexiteit tegenover BF16; lager is beter. De twee contextlengtes worden apart geëvalueerd. KL is een andere maat: het gemiddelde verschil tussen de kansverdelingen voor het volgende token op 170.884 tekst- en assistentposities, waarbij elk model zijn eigen experts kiest. KL nul zou identieke verdelingen betekenen.",[95,211,212,228],{},[98,213,214],{},[101,215,216,219,222,225],{},[104,217,218],{},"Tekst en contextlengte",[104,220,221],{"align":109},"Perplexiteit 16-bit",[104,223,224],{"align":109},"Perplexiteit 4-bit",[104,226,227],{"align":109},"Toename",[118,229,230,244,258,272],{},[101,231,232,235,238,241],{},[123,233,234],{},"WikiText-2-test, 512 tokens",[123,236,237],{"align":109},"4,589",[123,239,240],{"align":109},"4,629",[123,242,243],{"align":109},"0,87%",[101,245,246,249,252,255],{},[123,247,248],{},"WikiText-2-test, 4.096 tokens",[123,250,251],{"align":109},"3,929",[123,253,254],{"align":109},"3,961",[123,256,257],{"align":109},"0,80%",[101,259,260,263,266,269],{},[123,261,262],{},"Ongeziene tekst, 512 tokens",[123,264,265],{"align":109},"6,938",[123,267,268],{"align":109},"6,954",[123,270,271],{"align":109},"0,23%",[101,273,274,277,280,283],{},[123,275,276],{},"Ongeziene tekst, 4.096 tokens",[123,278,279],{"align":109},"6,163",[123,281,282],{"align":109},"6,187",[123,284,285],{"align":109},"0,38%",[10,287,288,289],{},"De ongeziene tekst bevat 22 documenten, samen 262.144 tokens, die nooit zijn gebruikt om de kwantisatie te maken. Perplexiteit gebruikt ruwe tekst zonder chattemplate en scoort de tweede helft van elk contextblok.",[23,290,291],{},[26,292,33],{"href":28,"ariaDescribedBy":293,"dataFootnoteRef":31,"id":294},[30],"user-content-fnref-model-6",[95,296,297,310],{},[98,298,299],{},[101,300,301,304,307],{},[104,302,303],{},"Configuratie",[104,305,306],{"align":109},"Bits per routed-expertgewicht",[104,308,309],{"align":109},"KL tegenover BF16",[118,311,312,323,334],{},[101,313,314,317,320],{},[123,315,316],{},"Twee correcte BF16-implementaties",[123,318,319],{"align":109},"16",[123,321,322],{"align":109},"0,0077",[101,324,325,328,331],{},[123,326,327],{},"Paiton 4-bit, INT6-trunk en FP8-cache",[123,329,330],{"align":109},"3,926",[123,332,333],{"align":109},"0,0306",[101,335,336,339,342],{},[123,337,338],{},"Standaard MXFP4-referentie, 8-bit trunk en BF16-cache",[123,340,341],{"align":109},"4,25",[123,343,344],{"align":109},"0,0515",[10,346,347,348,351,352,355,356,359,360],{},"De MXFP4-rij is ",[14,349,350],{},"onze eigen meting op dezelfde experts",", geen andere serving-engine. De geserveerde 4-bit configuratie heeft ",[14,353,354],{},"41% lagere KL"," en ongeveer ",[14,357,358],{},"8% minder bits per expertgewicht",", inclusief schalen. Ook de trunk en cache verschillen, dus dit isoleert niet het effect van het gewichtsformaat en betekent geen 41% hogere taaknauwkeurigheid.",[23,361,362],{},[26,363,33],{"href":28,"ariaDescribedBy":364,"dataFootnoteRef":31,"id":365},[30],"user-content-fnref-model-7",[10,367,368,369,372,373,376,377,380,381],{},"Over 44 apart gehouden documenten van 8K tot 32K tokens ligt de negatieve log-likelihood ",[14,370,371],{},"binnen 0,16% van BF16",". Een needle-opzoektest bij ",[14,374,375],{},"131.072 tokens"," geeft ",[14,378,379],{},"40 op 40",", met alle 419 antwoordtokens gelijk aan de referentie.",[23,382,383],{},[26,384,33],{"href":28,"ariaDescribedBy":385,"dataFootnoteRef":31,"id":386},[30],"user-content-fnref-model-8",[10,388,389,390],{},"Deze verdelings- en opzoekcontroles emuleren het standaard geserveerde rekenpad: INT6-trunk, int8-promptactivaties en FP8-KV-cache. De taakbenchmarks hierboven lopen via de server. De aparte 200K-modus gebruikt een 8-bit trunk en is niet afzonderlijk op nauwkeurigheid getest.",[23,391,392],{},[26,393,33],{"href":28,"ariaDescribedBy":394,"dataFootnoteRef":31,"id":395},[30],"user-content-fnref-model-9",[66,397,399],{"id":398},"bruikbare-snelheid-op-twee-workstation-gpus","Bruikbare snelheid op twee workstation-GPU's",[10,401,402,403,406,407],{},"De gepubliceerde prestatiemetingen gebruiken ",[14,404,405],{},"BetterBench 0.6.0, standaardprofiel",", via de exacte release-image en launcher, op twee R9700-kaarten in een PCIe 4.0 x16-host met 251 GiB RAM.",[23,408,409],{},[26,410,56],{"href":53,"ariaDescribedBy":411,"dataFootnoteRef":31,"id":412},[30],"user-content-fnref-fourbit-2",[85,414],{"kind":415},"concurrency",[10,417,418],{},[91,419,420],{},"Gegenereerde tokens per seconde; hoger is beter. Het cijfer voor één verzoek is een gewogen decodescore. Het cijfer voor acht verzoeken is de gezamenlijke serverdoorvoer uit een aparte gelijktijdigheidstaak, geen snelheid per gebruiker of vergelijking van achtvoudige schaalbaarheid.",[95,422,423,433],{},[98,424,425],{},[101,426,427,430],{},[104,428,429],{},"Meting",[104,431,432],{"align":109},"Resultaat",[118,434,435,443,451],{},[101,436,437,440],{},[123,438,439],{},"Gewogen decode met één verzoek, mediaan van drie runs",[123,441,442],{"align":109},"189,8 tokens\u002Fs",[101,444,445,448],{},[123,446,447],{},"Acht gelijktijdige verzoeken, samen",[123,449,450],{"align":109},"420,7 tokens\u002Fs",[101,452,453,456],{},[123,454,455],{},"Tijd tot eerste token bij korte prompts, mediaan",[123,457,458],{"align":109},"121 ms",[10,460,461,462,465,466,469,470,476],{},"Alle ",[14,463,464],{},"48 van 48 verzoeken"," werden afgerond bij gelijktijdigheid acht. BetterBench meet acht decodecategorieën, maar de gewogen score combineert er ",[14,467,468],{},"zes",": code 30%, redeneren 20%, proza en JSON elk 15%, bestandsbewerking en samenvatten elk 10%. Chat en rekenen worden gemeten zonder bij te dragen aan die score.",[23,471,472],{},[26,473,56],{"href":53,"ariaDescribedBy":474,"dataFootnoteRef":31,"id":475},[30],"user-content-fnref-fourbit-3",[23,477,478],{},[26,479,483],{"href":480,"ariaDescribedBy":481,"dataFootnoteRef":31,"id":482},"#user-content-fn-betterbench",[30],"user-content-fnref-betterbench","3",[189,485,487],{"id":486},"lange-prompts","Lange prompts",[10,489,490,491,494,495,498,499,502,503],{},"Prefill is het lezen van de invoer voordat het model begint te antwoorden. De lange-contextmodus verwerkt de nominale 64K-promptdiepte met ",[14,492,493],{},"6.991 invoertokens\u002Fs",". Een aparte controle met koude cache en ",[14,496,497],{},"precies 64.000 prompttokens"," meet ",[14,500,501],{},"7.162 tokens\u002Fs",".",[23,504,505],{},[26,506,56],{"href":53,"ariaDescribedBy":507,"dataFootnoteRef":31,"id":508},[30],"user-content-fnref-fourbit-4",[85,510],{"kind":511},"prefill",[10,513,514],{},[91,515,516,517,520],{},"Verwerkte invoertokens per seconde; hoger is beter. De BetterBench-promptdieptes zijn nominale instellingen, geen exacte tokenaantallen. Deze rijen gebruiken ",[74,518,519],{},"4bit-200k",", met een venster van 200.000 tokens en speculatieve decode uit. Ze staan los van de standaard decodemetingen.",[95,522,523,533],{},[98,524,525],{},[101,526,527,530],{},[104,528,529],{},"Instelling voor promptdiepte",[104,531,532],{"align":109},"Invoertokens\u002Fs",[118,534,535,543,551,559,567,575],{},[101,536,537,540],{},[123,538,539],{},"2K",[123,541,542],{"align":109},"5.564",[101,544,545,548],{},[123,546,547],{},"8K",[123,549,550],{"align":109},"6.771",[101,552,553,556],{},[123,554,555],{},"16K",[123,557,558],{"align":109},"6.641",[101,560,561,564],{},[123,562,563],{},"32K",[123,565,566],{"align":109},"7.044",[101,568,569,572],{},[123,570,571],{},"64K",[123,573,574],{"align":109},"6.991",[101,576,577,580],{},[123,578,579],{},"128K",[123,581,582],{"align":109},"6.857",[95,584,585,601],{},[98,586,587],{},[101,588,589,592,595,598],{},[104,590,591],{},"Modus",[104,593,594],{"align":109},"Contextvenster",[104,596,597],{},"Speculatieve decode",[104,599,600],{"align":109},"Gedeelde KV-cachecapaciteit",[118,602,603,619],{},[101,604,605,610,613,616],{},[123,606,607,609],{},[74,608,76],{},", standaard",[123,611,612],{"align":109},"98.304 tokens",[123,614,615],{},"Aan, diepte 3",[123,617,618],{"align":109},"305.338 tokens",[101,620,621,625,628,631],{},[123,622,623],{},[74,624,519],{},[123,626,627],{"align":109},"200.000 tokens",[123,629,630],{},"Uit",[123,632,633],{"align":109},"247.058 tokens",[10,635,636,637,640,641,647],{},"Beide gebruiken een ",[14,638,639],{},"FP8 E4M3-KV-cache",". De cachecapaciteit is gedeeld over verzoeken; ze is niet het maximale venster van één gesprek. In elk venster moeten de prompt, chatopmaak en het gegenereerde antwoord samen passen.",[23,642,643],{},[26,644,33],{"href":28,"ariaDescribedBy":645,"dataFootnoteRef":31,"id":646},[30],"user-content-fnref-model-10",[23,648,649],{},[26,650,654],{"href":651,"ariaDescribedBy":652,"dataFootnoteRef":31,"id":653},"#user-content-fn-modes",[30],"user-content-fnref-modes","4",[189,656,658],{"id":657},"sneller-herhaalde-gesprekken-met-de-ram-prefixcache","Sneller herhaalde gesprekken met de RAM-prefixcache",[10,660,661,662,668,669,502,672],{},"Codeagents sturen bij elke beurt hun hele gesprek opnieuw. De optionele ",[14,663,664,667],{},[74,665,666],{},"4bit-cache","-modus"," hergebruikt ongewijzigde prefixes in blokken van 2.048 tokens en bewaart uit VRAM verwijderde prefixblokken in een ",[14,670,671],{},"8 GiB pinned RAM-laag",[23,673,674],{},[26,675,56],{"href":53,"ariaDescribedBy":676,"dataFootnoteRef":31,"id":677},[30],"user-content-fnref-fourbit-5",[85,679],{"kind":680},"prefix-cache",[10,682,683],{},[91,684,685],{},"Tijd tot eerste token in aparte cachecontroles met herhaalde prompts; lager is beter. Een cachehit vraagt een herbruikbare prefix die nog in de cache staat. Dit zijn niet de BetterBench-prefillmetingen met koude cache.",[95,687,688,701],{},[98,689,690],{},[101,691,692,695,698],{},[104,693,694],{},"Herhaalde prompt",[104,696,697],{"align":109},"Eerste token zonder cachehit",[104,699,700],{"align":109},"Cachehit uit RAM-laag",[118,702,703,713,723],{},[101,704,705,707,710],{},[123,706,563],{},[123,708,709],{"align":109},"6,3 s",[123,711,712],{"align":109},"1,0 s",[101,714,715,717,720],{},[123,716,571],{},[123,718,719],{"align":109},"12,3 s",[123,721,722],{"align":109},"1,1 s",[101,724,725,728,731],{},[123,726,727],{},"90K",[123,729,730],{"align":109},"16,2 s",[123,732,722],{"align":109},[10,734,735,736,739,740,743,744,750],{},"De geteste RAM-hits geven ",[14,737,738],{},"identieke uitvoer als een koude start",". Daar staat ongeveer ",[14,741,742],{},"22% minder multi-userdoorvoer"," tegenover in de cachemodusvalidatie: 321,4 tegenover 411,3 tokens\u002Fs samen. Die validatiebaseline staat los van het BetterBench-hoofdcijfer van 420,7. Nieuwe prompts beginnen ook 0,1 tot 0,2 seconden later.",[23,745,746],{},[26,747,56],{"href":53,"ariaDescribedBy":748,"dataFootnoteRef":31,"id":749},[30],"user-content-fnref-fourbit-6",[23,751,752],{},[26,753,654],{"href":651,"ariaDescribedBy":754,"dataFootnoteRef":31,"id":755},[30],"user-content-fnref-modes-2",[10,757,758,759,762,763,765,766,768,769,771,772,502,775,781],{},"De volledige RAM-laag vraagt ongeveer ",[14,760,761],{},"108 GiB vrije GTT",", inclusief het extra pinned geheugen. Bij minder vrije GTT waarschuwt de launcher en verkleint of schakelt hij de RAM-laag uit, met behoud van prefixcaching in VRAM. Kies expliciet ",[74,764,666],{},"; de gewone modi ",[74,767,76],{}," en ",[74,770,519],{}," weigeren ",[74,773,774],{},"--prefix-caching",[23,776,777],{},[26,778,56],{"href":53,"ariaDescribedBy":779,"dataFootnoteRef":31,"id":780},[30],"user-content-fnref-fourbit-7",[23,782,783],{},[26,784,788],{"href":785,"ariaDescribedBy":786,"dataFootnoteRef":31,"id":787},"#user-content-fn-launcher",[30],"user-content-fnref-launcher","5",[66,790,792],{"id":791},"wat-4-bit-hier-betekent","Wat 4-bit hier betekent",[10,794,795,796,799,800,803,804,807,808],{},"Flash Next is een mixture-of-expertsmodel. In elke laag gebruiken de ",[14,797,798],{},"410 meest gebruikte experts INT4",", met GPTQ gekalibreerd in een geroteerde basis. De ",[14,801,802],{},"102 minst gebruikte experts gebruiken het 3-bit codebookformaat"," uit onze eerdere release. Samen komen de routed experts uit op gemiddeld ",[14,805,806],{},"3,926 bits per gewicht",", inclusief schalen. Dat gemiddelde geldt voor de gemengde expertset, niet voor het 3-bit formaat alleen.",[23,809,810],{},[26,811,33],{"href":28,"ariaDescribedBy":812,"dataFootnoteRef":31,"id":813},[30],"user-content-fnref-model-11",[10,815,816,817,820,821],{},"De standaard serving-modus gebruikt een ",[14,818,819],{},"6-bit trunk",", terwijl andere onderdelen 8-bit of hogere precisie behouden. De MTP-laag stelt speculatieve tokens voor die het doelmodel controleert. Het model is niet overal vier bits.",[23,822,823],{},[26,824,33],{"href":28,"ariaDescribedBy":825,"dataFootnoteRef":31,"id":826},[30],"user-content-fnref-model-12",[10,828,829,830,833,834,837],{},"Dit werk kostte ongeveer ",[14,831,832],{},"250 GPU-uren op een AMD Instinct MI355X-systeem"," voor kwantisatie, tuning en nauwkeurigheidstests, plus ongeveer ",[14,835,836],{},"100 uur op de twee R9700-kaarten"," voor tests van het geserveerde model. Die schattingen omvatten onze 3-bit en 4-bit Flash Next-releases samen.",[10,839,840,841,844,845,848,849],{},"De volledige 4-bit expertset past niet naast de runtime en cache op twee 32 GB-kaarten. Ongeveer ",[14,842,843],{},"20,8 GiB experts per kaart blijft in VRAM","; de GPU's lezen de rest uit pinned systeemgeheugen wanneer nodig. De launcher pint in totaal ongeveer ",[14,846,847],{},"96 GiB",", zo'n 55 GiB voor tabellen en 41 GiB voor expertkopieën. De geheugenbandbreedte en PCIe-verbindingen van de host zijn dus belangrijk.",[23,850,851],{},[26,852,56],{"href":53,"ariaDescribedBy":853,"dataFootnoteRef":31,"id":854},[30],"user-content-fnref-fourbit-8",[10,856,857,858,861,862,865,866],{},"De gemeten opstelling gebruikt GPU-gemapte ",[14,859,860],{},"GTT-geheugenallocaties",", met ongeveer ",[14,863,864],{},"98 GiB vrije GTT nodig als basis",". Daarom specificeren we een host met 256 GB. Bij minder GTT kan de launcher terugvallen op ROCm user-pointergeheugen, met een waarschuwing over lagere snelheid en mogelijke pauzes tijdens geheugencompactie op de host. Hij verandert geen kernelgeheugenlimieten.",[23,867,868],{},[26,869,56],{"href":53,"ariaDescribedBy":870,"dataFootnoteRef":31,"id":871},[30],"user-content-fnref-fourbit-9",[66,873,875],{"id":874},"start-de-release","Start de release",[10,877,878,879,882,883,886,887,768,890,893,894,897,898,901,902,905,906],{},"Gebruik Linux x86-64, ",[14,880,881],{},"twee Radeon AI PRO R9700-kaarten",", een ",[14,884,885],{},"ROCm 10-hostdriver",", Docker met toegang tot ",[74,888,889],{},"\u002Fdev\u002Fkfd",[74,891,892],{},"\u002Fdev\u002Fdri",", en Python ",[14,895,896],{},"3.10 of nieuwer"," met ",[74,899,900],{},"huggingface_hub"," geïnstalleerd. Voorzie ",[14,903,904],{},"133 GB voor gewichten",", plus de runtime-image van ongeveer 41 GB en werkruimte.",[23,907,908],{},[26,909,913],{"href":910,"ariaDescribedBy":911,"dataFootnoteRef":31,"id":912},"#user-content-fn-release",[30],"user-content-fnref-release","6",[10,915,916,917],{},"De commando's leggen de launcher vast en downloaden eerst de volledige modelrevisie. Dat vermijdt een probleem bij de eerste start in deze launcher: hij controleert de drafter vóór zijn automatische download. Gebruik een nieuwe checkout als je al lokale pluginwijzigingen hebt.",[23,918,919],{},[26,920,788],{"href":785,"ariaDescribedBy":921,"dataFootnoteRef":31,"id":922},[30],"user-content-fnref-launcher-2",[924,925,929],"pre",{"className":926,"code":927,"language":928,"meta":31,"style":31},"language-bash shiki shiki-themes github-light github-dark","git clone https:\u002F\u002Fgithub.com\u002FEliovp-BV\u002Fpaiton-vllm-plugin.git\ncd paiton-vllm-plugin\ngit checkout a985fa598d9a3c7536720304830a0e427f3af1f2\n\npython3 -m venv .venv\n. .venv\u002Fbin\u002Factivate\npython3 -m pip install huggingface_hub\npython3 - \u003C\u003C'PY'\nfrom huggingface_hub import snapshot_download\nsnapshot_download(\n    repo_id=\"EliovpAI\u002FQwen3.8-Flash-Next-W4A8-Paiton-RDNA4\",\n    revision=\"9ec8e306503d5f9c9e8fd9c0d77de8fa63428888\",\n    local_dir=\"flashnext-w4a8\",\n)\nPY\n(cd flashnext-w4a8 && sha256sum -c SHA256SUMS)\n\npython3 models\u002FQwen3.8-Flash-Next\u002Flaunch-flashnext.py \\\n  --mode 4bit --weights \"$PWD\u002Fflashnext-w4a8\" --dry-run\nbash models\u002FQwen3.8-Flash-Next\u002Frun-flashnext-4bit.sh \\\n  --weights \"$PWD\u002Fflashnext-w4a8\" --host 127.0.0.1\n","bash",[74,930,931,947,957,968,975,990,998,1014,1029,1035,1041,1047,1053,1059,1065,1071,1097,1102,1113,1137,1147],{"__ignoreMap":31},[932,933,936,940,944],"span",{"class":934,"line":935},"line",1,[932,937,939],{"class":938},"sScJk","git",[932,941,943],{"class":942},"sZZnC"," clone",[932,945,946],{"class":942}," https:\u002F\u002Fgithub.com\u002FEliovp-BV\u002Fpaiton-vllm-plugin.git\n",[932,948,950,954],{"class":934,"line":949},2,[932,951,953],{"class":952},"sj4cs","cd",[932,955,956],{"class":942}," paiton-vllm-plugin\n",[932,958,960,962,965],{"class":934,"line":959},3,[932,961,939],{"class":938},[932,963,964],{"class":942}," checkout",[932,966,967],{"class":942}," a985fa598d9a3c7536720304830a0e427f3af1f2\n",[932,969,971],{"class":934,"line":970},4,[932,972,974],{"emptyLinePlaceholder":973},true,"\n",[932,976,978,981,984,987],{"class":934,"line":977},5,[932,979,980],{"class":938},"python3",[932,982,983],{"class":952}," -m",[932,985,986],{"class":942}," venv",[932,988,989],{"class":942}," .venv\n",[932,991,993,995],{"class":934,"line":992},6,[932,994,502],{"class":952},[932,996,997],{"class":942}," .venv\u002Fbin\u002Factivate\n",[932,999,1001,1003,1005,1008,1011],{"class":934,"line":1000},7,[932,1002,980],{"class":938},[932,1004,983],{"class":952},[932,1006,1007],{"class":942}," pip",[932,1009,1010],{"class":942}," install",[932,1012,1013],{"class":942}," huggingface_hub\n",[932,1015,1017,1019,1022,1026],{"class":934,"line":1016},8,[932,1018,980],{"class":938},[932,1020,1021],{"class":942}," -",[932,1023,1025],{"class":1024},"szBVR"," \u003C\u003C",[932,1027,1028],{"class":942},"'PY'\n",[932,1030,1032],{"class":934,"line":1031},9,[932,1033,1034],{"class":942},"from huggingface_hub import snapshot_download\n",[932,1036,1038],{"class":934,"line":1037},10,[932,1039,1040],{"class":942},"snapshot_download(\n",[932,1042,1044],{"class":934,"line":1043},11,[932,1045,1046],{"class":942},"    repo_id=\"EliovpAI\u002FQwen3.8-Flash-Next-W4A8-Paiton-RDNA4\",\n",[932,1048,1050],{"class":934,"line":1049},12,[932,1051,1052],{"class":942},"    revision=\"9ec8e306503d5f9c9e8fd9c0d77de8fa63428888\",\n",[932,1054,1056],{"class":934,"line":1055},13,[932,1057,1058],{"class":942},"    local_dir=\"flashnext-w4a8\",\n",[932,1060,1062],{"class":934,"line":1061},14,[932,1063,1064],{"class":942},")\n",[932,1066,1068],{"class":934,"line":1067},15,[932,1069,1070],{"class":942},"PY\n",[932,1072,1074,1078,1080,1083,1086,1089,1092,1095],{"class":934,"line":1073},16,[932,1075,1077],{"class":1076},"sVt8B","(",[932,1079,953],{"class":952},[932,1081,1082],{"class":942}," flashnext-w4a8",[932,1084,1085],{"class":1076}," && ",[932,1087,1088],{"class":938},"sha256sum",[932,1090,1091],{"class":952}," -c",[932,1093,1094],{"class":942}," SHA256SUMS",[932,1096,1064],{"class":1076},[932,1098,1100],{"class":934,"line":1099},17,[932,1101,974],{"emptyLinePlaceholder":973},[932,1103,1105,1107,1110],{"class":934,"line":1104},18,[932,1106,980],{"class":938},[932,1108,1109],{"class":942}," models\u002FQwen3.8-Flash-Next\u002Flaunch-flashnext.py",[932,1111,1112],{"class":952}," \\\n",[932,1114,1116,1119,1122,1125,1128,1131,1134],{"class":934,"line":1115},19,[932,1117,1118],{"class":952},"  --mode",[932,1120,1121],{"class":942}," 4bit",[932,1123,1124],{"class":952}," --weights",[932,1126,1127],{"class":942}," \"",[932,1129,1130],{"class":1076},"$PWD",[932,1132,1133],{"class":942},"\u002Fflashnext-w4a8\"",[932,1135,1136],{"class":952}," --dry-run\n",[932,1138,1140,1142,1145],{"class":934,"line":1139},20,[932,1141,928],{"class":938},[932,1143,1144],{"class":942}," models\u002FQwen3.8-Flash-Next\u002Frun-flashnext-4bit.sh",[932,1146,1112],{"class":952},[932,1148,1150,1153,1155,1157,1159,1162],{"class":934,"line":1149},21,[932,1151,1152],{"class":952},"  --weights",[932,1154,1127],{"class":942},[932,1156,1130],{"class":1076},[932,1158,1133],{"class":942},[932,1160,1161],{"class":952}," --host",[932,1163,1164],{"class":952}," 127.0.0.1\n",[10,1166,1167,1168,1171,1172,1175,1176,1179,1180,502,1183,1189],{},"De dry run toont RAM, GTT-limieten en GPU-verbindingscontroles. De launcher haalt de runtime op via digest. Na de gewichtendownload duurt de eerste start ongeveer ",[14,1169,1170],{},"vijf tot zes minuten","; wacht op ",[74,1173,1174],{},"launcher: READY on port …",". De API staat op ",[74,1177,1178],{},"http:\u002F\u002F127.0.0.1:18982\u002Fv1",", met modelnaam ",[74,1181,1182],{},"Qwen3.8-Flash-Next",[23,1184,1185],{},[26,1186,913],{"href":910,"ariaDescribedBy":1187,"dataFootnoteRef":31,"id":1188},[30],"user-content-fnref-release-2",[23,1190,1191],{},[26,1192,654],{"href":651,"ariaDescribedBy":1193,"dataFootnoteRef":31,"id":1194},[30],"user-content-fnref-modes-3",[10,1196,1197,1198,1201,1202,1205,1206,1209,1210],{},"De standaardserver luistert op ",[14,1199,1200],{},"alle netwerkinterfaces zonder API-sleutel",". Het voorbeeld beperkt dat tot localhost. Beveilig toegang voor vertrouwde externe clients met een firewall of stel ",[74,1203,1204],{},"PAITON_API_KEY"," in de omgeving in. Verkies de omgevingsvariabele boven ",[74,1207,1208],{},"--api-key",", die de sleutel zichtbaar maakt in de proceslijst.",[23,1211,1212],{},[26,1213,913],{"href":910,"ariaDescribedBy":1214,"dataFootnoteRef":31,"id":1215},[30],"user-content-fnref-release-3",[10,1217,1218],{},"Stop de draaiende server voordat je een andere modus kiest:",[924,1220,1222],{"className":926,"code":1221,"language":928,"meta":31,"style":31},"# 200K-venster, speculatieve decode uit\nbash models\u002FQwen3.8-Flash-Next\u002Frun-flashnext-4bit-200k.sh \\\n  --weights \"$PWD\u002Fflashnext-w4a8\" --host 127.0.0.1\n\n# Herhaalde codegesprekken, optionele RAM-prefixcache\nbash models\u002FQwen3.8-Flash-Next\u002Frun-flashnext-4bit-cache.sh \\\n  --weights \"$PWD\u002Fflashnext-w4a8\" --host 127.0.0.1\n",[74,1223,1224,1230,1239,1253,1257,1262,1271],{"__ignoreMap":31},[932,1225,1226],{"class":934,"line":935},[932,1227,1229],{"class":1228},"sJ8bj","# 200K-venster, speculatieve decode uit\n",[932,1231,1232,1234,1237],{"class":934,"line":949},[932,1233,928],{"class":938},[932,1235,1236],{"class":942}," models\u002FQwen3.8-Flash-Next\u002Frun-flashnext-4bit-200k.sh",[932,1238,1112],{"class":952},[932,1240,1241,1243,1245,1247,1249,1251],{"class":934,"line":959},[932,1242,1152],{"class":952},[932,1244,1127],{"class":942},[932,1246,1130],{"class":1076},[932,1248,1133],{"class":942},[932,1250,1161],{"class":952},[932,1252,1164],{"class":952},[932,1254,1255],{"class":934,"line":970},[932,1256,974],{"emptyLinePlaceholder":973},[932,1258,1259],{"class":934,"line":977},[932,1260,1261],{"class":1228},"# Herhaalde codegesprekken, optionele RAM-prefixcache\n",[932,1263,1264,1266,1269],{"class":934,"line":992},[932,1265,928],{"class":938},[932,1267,1268],{"class":942}," models\u002FQwen3.8-Flash-Next\u002Frun-flashnext-4bit-cache.sh",[932,1270,1112],{"class":952},[932,1272,1273,1275,1277,1279,1281,1283],{"class":934,"line":1000},[932,1274,1152],{"class":952},[932,1276,1127],{"class":942},[932,1278,1130],{"class":1076},[932,1280,1133],{"class":942},[932,1282,1161],{"class":952},[932,1284,1164],{"class":952},[10,1286,1287,1288,1294,1295],{},"De ",[26,1289,1293],{"href":1290,"rel":1291},"https:\u002F\u002Fgithub.com\u002FEliovp-BV\u002Fpaiton-vllm-plugin\u002Fblob\u002Fa985fa598d9a3c7536720304830a0e427f3af1f2\u002Fmodels\u002FQwen3.8-Flash-Next\u002FREADME-4bit.md",[1292],"nofollow","4-bit installatiehandleiding"," beschrijft de opties. Deze gewichten vragen de Paiton-runtime en plugin; standaard modelloaders ondersteunen het formaat niet.",[23,1296,1297],{},[26,1298,33],{"href":28,"ariaDescribedBy":1299,"dataFootnoteRef":31,"id":1300},[30],"user-content-fnref-model-13",[66,1302,1304],{"id":1303},"ook-in-deze-release","Ook in deze release",[10,1306,1287,1307,1310,1311],{},[14,1308,1309],{},"3-bit Flash Next-launcher"," krijgt een stabielere start op drukke hosts, controles voor GPU-verbindingen en hostgeheugen, en expliciete prefixcacheblokken van 2.048 tokens. De standaardbinding aan alle interfaces en optionele API-sleutel gelden voor beide releases. De 3-bit gewichten en runtime-image zijn ongewijzigd.",[23,1312,1313],{},[26,1314,1318],{"href":1315,"ariaDescribedBy":1316,"dataFootnoteRef":31,"id":1317},"#user-content-fn-notes",[30],"user-content-fnref-notes","7",[10,1320,1321,1324,1325,1331,1332,1335,1336],{},[14,1322,1323],{},"Qwen3.8 27B op één R9700"," krijgt ook een launcherupdate. Zijn ",[14,1326,1327,1328],{},"3-bit ",[74,1329,1330],{},"--mode long"," houdt nu ",[14,1333,1334],{},"316.325 tokens gedeelde cache"," vast, en de opstartgeheugenpieken zijn lager in de 3-bit modi. De MXFP4-configuraties zijn ongewijzigd.",[23,1337,1338],{},[26,1339,1343],{"href":1340,"ariaDescribedBy":1341,"dataFootnoteRef":31,"id":1342},"#user-content-fn-twentyseven",[30],"user-content-fnref-twentyseven","8",[66,1345,1347],{"id":1346},"op-weg-naar-hosts-met-128-gb","Op weg naar hosts met 128 GB",[10,1349,1350,1351,1354],{},"Niet iedereen heeft 256 GB RAM. We werken aan een 4-bit configuratie die de grote n-gram-tabel in gewoon, niet-gepind geheugen houdt, met als doel bit-identieke uitvoer te behouden. Het doel is ",[14,1352,1353],{},"machines met 128 GB",". Dit is werk in uitvoering, geen uitgebrachte of gekwalificeerde configuratie.",[66,1356,1358],{"id":1357},"credits-en-licenties","Credits en licenties",[10,1360,1361,1362,1365,1366,1371],{},"Qwen3.8 Flash Next is van het Qwen-team; vLLM levert het serving-framework en BetterBench de prestatietests. De modelgewichten blijven onder ",[14,1363,1364],{},"Qwen Community License 1.0",", met voorwaarden voor commercieel gebruik. Bekijk de ",[26,1367,1370],{"href":1368,"rel":1369},"https:\u002F\u002Fhuggingface.co\u002FQwen\u002FQwen3.8-Flash-Next\u002Fblob\u002Fde4b8e4d43b917e7706784d8bb445c9af86a3540\u002FLICENSE",[1292],"upstreamlicentie"," vóór inzet.",[10,1373,1374,1375,1380,1381,1385,1386,1390],{},"Lees de ",[26,1376,1379],{"href":1377,"rel":1378},"https:\u002F\u002Fhuggingface.co\u002FEliovpAI\u002FQwen3.8-Flash-Next-W4A8-Paiton-RDNA4\u002Fblob\u002F9ec8e306503d5f9c9e8fd9c0d77de8fa63428888\u002FREADME.md",[1292],"4-bit modelkaart en nauwkeurigheidsdetails",", ontdek ",[26,1382,1384],{"href":1383},"\u002Fnl\u002Fproducts\u002Fpaiton","Paiton",", of ",[26,1387,1389],{"href":1388},"\u002Fnl\u002Fcontact","neem contact op"," over een lokale AMD-AI-workload.",[1392,1393,1396,1401],"section",{"className":1394,"dataFootnotes":31},[1395],"footnotes",[66,1397,1400],{"className":1398,"id":30},[1399],"sr-only","Footnotes",[1402,1403,1404,1510,1578,1591,1618,1638,1665,1678],"ol",{},[1405,1406,1408,1412,1413,1420,1421,1420,1428,1420,1435,1420,1442,1420,1449,1420,1456,1420,1463,1420,1470,1420,1478,1420,1486,1420,1494,1420,1502],"li",{"id":1407},"user-content-fn-model",[26,1409,1411],{"href":1377,"rel":1410},[1292],"W4A8-modelkaart en evaluatiemethoden, vastgelegde revisie",". ",[26,1414,1419],{"href":1415,"ariaLabel":1416,"className":1417,"dataFootnoteBackref":31},"#user-content-fnref-model","Back to reference 1",[1418],"data-footnote-backref","↩"," ",[26,1422,1419,1426],{"href":1423,"ariaLabel":1424,"className":1425,"dataFootnoteBackref":31},"#user-content-fnref-model-2","Back to reference 1-2",[1418],[23,1427,56],{},[26,1429,1419,1433],{"href":1430,"ariaLabel":1431,"className":1432,"dataFootnoteBackref":31},"#user-content-fnref-model-3","Back to reference 1-3",[1418],[23,1434,483],{},[26,1436,1419,1440],{"href":1437,"ariaLabel":1438,"className":1439,"dataFootnoteBackref":31},"#user-content-fnref-model-4","Back to reference 1-4",[1418],[23,1441,654],{},[26,1443,1419,1447],{"href":1444,"ariaLabel":1445,"className":1446,"dataFootnoteBackref":31},"#user-content-fnref-model-5","Back to reference 1-5",[1418],[23,1448,788],{},[26,1450,1419,1454],{"href":1451,"ariaLabel":1452,"className":1453,"dataFootnoteBackref":31},"#user-content-fnref-model-6","Back to reference 1-6",[1418],[23,1455,913],{},[26,1457,1419,1461],{"href":1458,"ariaLabel":1459,"className":1460,"dataFootnoteBackref":31},"#user-content-fnref-model-7","Back to reference 1-7",[1418],[23,1462,1318],{},[26,1464,1419,1468],{"href":1465,"ariaLabel":1466,"className":1467,"dataFootnoteBackref":31},"#user-content-fnref-model-8","Back to reference 1-8",[1418],[23,1469,1343],{},[26,1471,1419,1475],{"href":1472,"ariaLabel":1473,"className":1474,"dataFootnoteBackref":31},"#user-content-fnref-model-9","Back to reference 1-9",[1418],[23,1476,1477],{},"9",[26,1479,1419,1483],{"href":1480,"ariaLabel":1481,"className":1482,"dataFootnoteBackref":31},"#user-content-fnref-model-10","Back to reference 1-10",[1418],[23,1484,1485],{},"10",[26,1487,1419,1491],{"href":1488,"ariaLabel":1489,"className":1490,"dataFootnoteBackref":31},"#user-content-fnref-model-11","Back to reference 1-11",[1418],[23,1492,1493],{},"11",[26,1495,1419,1499],{"href":1496,"ariaLabel":1497,"className":1498,"dataFootnoteBackref":31},"#user-content-fnref-model-12","Back to reference 1-12",[1418],[23,1500,1501],{},"12",[26,1503,1419,1507],{"href":1504,"ariaLabel":1505,"className":1506,"dataFootnoteBackref":31},"#user-content-fnref-model-13","Back to reference 1-13",[1418],[23,1508,1509],{},"13",[1405,1511,1513,1412,1517,1420,1522,1420,1529,1420,1536,1420,1543,1420,1550,1420,1557,1420,1564,1420,1571],{"id":1512},"user-content-fn-fourbit",[26,1514,1516],{"href":1290,"rel":1515},[1292],"4-bit nauwkeurigheid, snelheid en hardware, vastgelegde release",[26,1518,1419],{"href":1519,"ariaLabel":1520,"className":1521,"dataFootnoteBackref":31},"#user-content-fnref-fourbit","Back to reference 2",[1418],[26,1523,1419,1527],{"href":1524,"ariaLabel":1525,"className":1526,"dataFootnoteBackref":31},"#user-content-fnref-fourbit-2","Back to reference 2-2",[1418],[23,1528,56],{},[26,1530,1419,1534],{"href":1531,"ariaLabel":1532,"className":1533,"dataFootnoteBackref":31},"#user-content-fnref-fourbit-3","Back to reference 2-3",[1418],[23,1535,483],{},[26,1537,1419,1541],{"href":1538,"ariaLabel":1539,"className":1540,"dataFootnoteBackref":31},"#user-content-fnref-fourbit-4","Back to reference 2-4",[1418],[23,1542,654],{},[26,1544,1419,1548],{"href":1545,"ariaLabel":1546,"className":1547,"dataFootnoteBackref":31},"#user-content-fnref-fourbit-5","Back to reference 2-5",[1418],[23,1549,788],{},[26,1551,1419,1555],{"href":1552,"ariaLabel":1553,"className":1554,"dataFootnoteBackref":31},"#user-content-fnref-fourbit-6","Back to reference 2-6",[1418],[23,1556,913],{},[26,1558,1419,1562],{"href":1559,"ariaLabel":1560,"className":1561,"dataFootnoteBackref":31},"#user-content-fnref-fourbit-7","Back to reference 2-7",[1418],[23,1563,1318],{},[26,1565,1419,1569],{"href":1566,"ariaLabel":1567,"className":1568,"dataFootnoteBackref":31},"#user-content-fnref-fourbit-8","Back to reference 2-8",[1418],[23,1570,1343],{},[26,1572,1419,1576],{"href":1573,"ariaLabel":1574,"className":1575,"dataFootnoteBackref":31},"#user-content-fnref-fourbit-9","Back to reference 2-9",[1418],[23,1577,1477],{},[1405,1579,1581,1412,1586],{"id":1580},"user-content-fn-betterbench",[26,1582,1585],{"href":1583,"rel":1584},"https:\u002F\u002Fgithub.com\u002FGGZ14\u002FBetterBench\u002Fblob\u002Fd00ad5ec8098c06584a88ec3468bacd37d5ed098\u002Fconfig\u002Fdefault.json",[1292],"BetterBench 0.6.0-workloadgewichten",[26,1587,1419],{"href":1588,"ariaLabel":1589,"className":1590,"dataFootnoteBackref":31},"#user-content-fnref-betterbench","Back to reference 3",[1418],[1405,1592,1594,1412,1599,1420,1604,1420,1611],{"id":1593},"user-content-fn-modes",[26,1595,1598],{"href":1596,"rel":1597},"https:\u002F\u002Fgithub.com\u002FEliovp-BV\u002Fpaiton-vllm-plugin\u002Fblob\u002Fa985fa598d9a3c7536720304830a0e427f3af1f2\u002Fmodels\u002FQwen3.8-Flash-Next\u002Fmodes.json",[1292],"Vastgelegde gewichten, runtimedigest en serving-modi",[26,1600,1419],{"href":1601,"ariaLabel":1602,"className":1603,"dataFootnoteBackref":31},"#user-content-fnref-modes","Back to reference 4",[1418],[26,1605,1419,1609],{"href":1606,"ariaLabel":1607,"className":1608,"dataFootnoteBackref":31},"#user-content-fnref-modes-2","Back to reference 4-2",[1418],[23,1610,56],{},[26,1612,1419,1616],{"href":1613,"ariaLabel":1614,"className":1615,"dataFootnoteBackref":31},"#user-content-fnref-modes-3","Back to reference 4-3",[1418],[23,1617,483],{},[1405,1619,1621,1412,1626,1420,1631],{"id":1620},"user-content-fn-launcher",[26,1622,1625],{"href":1623,"rel":1624},"https:\u002F\u002Fgithub.com\u002FEliovp-BV\u002Fpaiton-vllm-plugin\u002Fblob\u002Fa985fa598d9a3c7536720304830a0e427f3af1f2\u002Fmodels\u002FQwen3.8-Flash-Next\u002Flaunch-flashnext.py",[1292],"Publieke launchercontroles en RAM-laagdimensionering, vastgelegde release",[26,1627,1419],{"href":1628,"ariaLabel":1629,"className":1630,"dataFootnoteBackref":31},"#user-content-fnref-launcher","Back to reference 5",[1418],[26,1632,1419,1636],{"href":1633,"ariaLabel":1634,"className":1635,"dataFootnoteBackref":31},"#user-content-fnref-launcher-2","Back to reference 5-2",[1418],[23,1637,56],{},[1405,1639,1641,1412,1646,1420,1651,1420,1658],{"id":1640},"user-content-fn-release",[26,1642,1645],{"href":1643,"rel":1644},"https:\u002F\u002Fgithub.com\u002FEliovp-BV\u002Fpaiton-vllm-plugin\u002Fblob\u002Fa985fa598d9a3c7536720304830a0e427f3af1f2\u002Fmodels\u002FQwen3.8-Flash-Next\u002FREADME.md",[1292],"Launchervoorwaarden en netwerkconfiguratie, vastgelegde release",[26,1647,1419],{"href":1648,"ariaLabel":1649,"className":1650,"dataFootnoteBackref":31},"#user-content-fnref-release","Back to reference 6",[1418],[26,1652,1419,1656],{"href":1653,"ariaLabel":1654,"className":1655,"dataFootnoteBackref":31},"#user-content-fnref-release-2","Back to reference 6-2",[1418],[23,1657,56],{},[26,1659,1419,1663],{"href":1660,"ariaLabel":1661,"className":1662,"dataFootnoteBackref":31},"#user-content-fnref-release-3","Back to reference 6-3",[1418],[23,1664,483],{},[1405,1666,1668,1412,1673],{"id":1667},"user-content-fn-notes",[26,1669,1672],{"href":1670,"rel":1671},"https:\u002F\u002Fgithub.com\u002FEliovp-BV\u002Fpaiton-vllm-plugin\u002Fblob\u002Fa985fa598d9a3c7536720304830a0e427f3af1f2\u002Fmodels\u002FQwen3.8-Flash-Next\u002FRELEASE-NOTES.md",[1292],"Flash Next-releasenotities, vastgelegde release",[26,1674,1419],{"href":1675,"ariaLabel":1676,"className":1677,"dataFootnoteBackref":31},"#user-content-fnref-notes","Back to reference 7",[1418],[1405,1679,1681,1412,1686],{"id":1680},"user-content-fn-twentyseven",[26,1682,1685],{"href":1683,"rel":1684},"https:\u002F\u002Fgithub.com\u002FEliovp-BV\u002Fpaiton-vllm-plugin\u002Fblob\u002Fa985fa598d9a3c7536720304830a0e427f3af1f2\u002Fmodels\u002FQwen3.8-MXFP4-DFlash2\u002FREFERENCE.md#launcher-update-11-october-2026",[1292],"27B 3-bit launcherupdate van 11 oktober, vastgelegde release",[26,1687,1419],{"href":1688,"ariaLabel":1689,"className":1690,"dataFootnoteBackref":31},"#user-content-fnref-twentyseven","Back to reference 8",[1418],[1692,1693,1694],"style",{},"html pre.shiki code .sScJk, html code.shiki .sScJk{--shiki-default:#6F42C1;--shiki-dark:#B392F0}html pre.shiki code .sZZnC, html code.shiki .sZZnC{--shiki-default:#032F62;--shiki-dark:#9ECBFF}html pre.shiki code .sj4cs, html code.shiki .sj4cs{--shiki-default:#005CC5;--shiki-dark:#79B8FF}html pre.shiki code .szBVR, html code.shiki .szBVR{--shiki-default:#D73A49;--shiki-dark:#F97583}html pre.shiki code .sVt8B, html code.shiki .sVt8B{--shiki-default:#24292E;--shiki-dark:#E1E4E8}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html pre.shiki code .sJ8bj, html code.shiki .sJ8bj{--shiki-default:#6A737D;--shiki-dark:#6A737D}",{"title":31,"searchDepth":949,"depth":949,"links":1696},[1697,1700,1704,1705,1706,1707,1708,1709],{"id":68,"depth":949,"text":69,"children":1698},[1699],{"id":191,"depth":959,"text":192},{"id":398,"depth":949,"text":399,"children":1701},[1702,1703],{"id":486,"depth":959,"text":487},{"id":657,"depth":959,"text":658},{"id":791,"depth":949,"text":792},{"id":874,"depth":949,"text":875},{"id":1303,"depth":949,"text":1304},{"id":1346,"depth":949,"text":1347},{"id":1357,"depth":949,"text":1358},{"id":30,"depth":949,"text":1400},[1384,1711,1712,1713,1714],"AMD Radeon","Lokale AI","Qwen","Kwantisatie","2026-10-12T15:00:00Z","Paiton draait Qwen3.8 Flash Next in 4-bit op twee R9700-kaarten: 96,8% GSM8K, 96,3% HumanEval, 189,8 tokens\u002Fs en een optionele RAM-prefixcache. Kwaliteit, snelheid en installatie.","md","4-bit op twee kaarten, getest tegenover 16-bit.","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-flash-next-4bit\u002Fhero-nl.webp",{},"https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-flash-next-4bit-radeon-ai-pro-r9700","\u002Fblog\u002Fpaiton-qwen38-flash-next-4bit-radeon-ai-pro-r9700",{"title":5,"description":1716},"paiton-qwen38-flash-next-4bit-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-flash-next-4bit\u002Fsocial-nl.webp","blog\u002Fpaiton-qwen38-flash-next-4bit-radeon-ai-pro-r9700",null,"o0LSKqgfoVVaN4eXXb8MtBSSlbOgRnO08cdHS0r3Tvc",[1730,1732,1741,1750,1760,1773,1783,1795,1805,1818,1827,1841,1873,1885,1907,1925,1944,1963,1981,1998,2010,2026,2041,2053,2062,2070,2085,2097,2108,2119,2129,2142,2152,2165,2176,2186,2197,2206,2218,2229,2238],{"path":1722,"title":5,"description":1716,"date":1715,"slug":1724,"image":1719,"originalUrl":1721,"categories":1731},[1384,1711,1712,1713,1714],{"path":1733,"title":1734,"description":1735,"date":1736,"slug":1737,"image":1738,"originalUrl":1739,"categories":1740},"\u002Fblog\u002Fpaiton-qwen38-flash-next-radeon-ai-pro-r9700","Qwen3.8 Flash Next op 2 × Radeon AI PRO R9700: 216 tokens\u002Fs, 200K-context","Paiton draait Qwen3.8 Flash Next met 3-bit experts op twee R9700-kaarten: 216,3 tokens\u002Fs, 565,1 tokens\u002Fs samen en een aparte 200K-modus. Metingen, kwaliteit en installatie.","2026-10-10T10:30:00Z","paiton-qwen38-flash-next-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-flash-next\u002Fhero-nl.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-flash-next-radeon-ai-pro-r9700",[1384,1711,1712,1713,1714],{"path":1742,"title":1743,"description":1744,"date":1745,"slug":1746,"image":1747,"originalUrl":1748,"categories":1749},"\u002Fblog\u002Fpaiton-qwen38-w3a4-radeon-ai-pro-r9700","Qwen3.8 27B op 1 × Radeon AI PRO R9700: 3-bit gewichten, 20% snellere decode","Qwen3.8 27B op één R9700: 19,9% snellere gewogen decode, een nieuwe 4-bit cache, 200K-context en optionele beeldinvoer. Metingen en Paiton-installatie.","2026-09-27T09:00:00Z","paiton-qwen38-w3a4-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-w3a4\u002Fhero-nl.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-w3a4-radeon-ai-pro-r9700",[1384,1711,1712,1713,1714],{"path":1751,"title":1752,"description":1753,"date":1754,"slug":1755,"image":1756,"originalUrl":1757,"categories":1758},"\u002Fblog\u002Fpaiton-qwen-image-21-radeon-ai-pro-r9700","Qwen-Image 2.1 op 1 × Radeon AI PRO R9700: 2048×2048-beelden in 103 seconden","Genereer lokaal Qwen-Image 2.1-beelden van 2048×2048 pixels met 1 × Radeon AI PRO R9700. De Paiton v1.0.2-container mat 103,29 seconden per opgewarmd verzoek, inclusief de PNG-respons.","2026-09-23T09:00:00Z","paiton-qwen-image-21-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen-image-21\u002Fhero-nl.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen-image-21-radeon-ai-pro-r9700",[1384,1711,1712,1759,1713],"Beeldgeneratie",{"path":1761,"title":1762,"description":1763,"date":1764,"slug":1765,"image":1766,"originalUrl":1767,"categories":1768},"\u002Fblog\u002Fpaiton-qwen38-mxfp4-dflash2-r9700","Qwen3.8: 400,7 tok\u002Fs op één R9700 | Paiton","Qwen3.8 op één R9700: 400,7 tok\u002Fs met ROCm 10 en vLLM 0.29, plus publieke 200K\u002F220K-chatprofielen. Benchmarks, beperkingen en startopdrachten.","2026-09-16T07:30:00Z","paiton-qwen38-mxfp4-dflash2-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-qwen38-mxfp4\u002Fupdate-2026-09-19\u002Fhero.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-mxfp4-dflash2-r9700",[1384,1711,1712,1769,1770,1771,1772],"AI-inferentie","Inferentie-optimalisatie","Grote taalmodellen","vLLM",{"path":1774,"title":1775,"description":1776,"date":1777,"slug":1778,"image":1779,"originalUrl":1780,"categories":1781},"\u002Fblog\u002Fpaiton-qwen38-neo-gguf-vllm-r9700","Qwen3.8 GGUF in vLLM: sneller antwoord op één Radeon","Draai de originele NEO CODER MAX GGUF met Paiton in vLLM op een R9700. Bekijk de gemeten responstijden, beeldinvoer en lokale installatie.","2026-09-14T07:30:00Z","paiton-qwen38-neo-gguf-vllm-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-neo-gguf\u002F00-hero-neo-gguf-r9700.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-neo-gguf-vllm-r9700",[1384,1711,1712,1782,1772],"GGUF",{"path":1784,"title":1785,"description":1786,"date":1787,"slug":1788,"image":1789,"originalUrl":1790,"categories":1791},"\u002Fblog\u002Fpaiton-minimax-h3-radeon-ai-pro-r9700","MiniMax H3 op Radeon: 15 seconden video met stereogeluid","Paiton genereert lokaal 15 seconden MiniMax H3-video met stereogeluid op één Radeon AI PRO R9700 in 5 min 33 s, met 16,7% minder wachttijd dan stock.","2026-09-09T07:30:00Z","paiton-minimax-h3-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-minimax-h3\u002F00-featured-minimax-h3-r9700.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-minimax-h3-radeon-ai-pro-r9700",[1384,1711,1712,1792,1793,1794],"Videogeneratie","MiniMax H3","ComfyUI",{"path":1796,"title":1797,"description":1798,"date":1799,"slug":1800,"image":1801,"originalUrl":1802,"categories":1803},"\u002Fblog\u002Fpaiton-flux2-klein-radeon-ai-pro-r9700","Lokale FLUX.2 klein op Radeon AI PRO R9700: sneller beelden genereren met minder VRAM","Paiton genereert FLUX.2 klein-beelden van 1024 × 1024 in 1,054 seconden op een R9700, met 16,2% minder generatietijd en 33,4% minder piekallocatie in Torch.","2026-09-07T09:00:00","paiton-flux2-klein-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-flux2-klein\u002Ffox-paiton.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-flux2-klein-radeon-ai-pro-r9700",[1384,1711,1712,1759,1804,1794],"FLUX",{"path":1806,"title":1807,"description":1808,"date":1809,"slug":1810,"image":1811,"originalUrl":1812,"categories":1813},"\u002Fblog\u002Fpaiton-ornith15-radeon-ai-pro-r9700","Ornith 1.5 haalt 44,6 tok\u002Fs op één Radeon AI PRO R9700","Paiton draait Ornith 1.5 35B A3B op één Radeon AI PRO R9700 met 44,63 outputtokens per seconde, 27% sneller en met 21,3% lagere gemodelleerde kosten.","2026-09-05T09:00:00","paiton-ornith15-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-ornith15\u002F00-featured-ornith15-r9700.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-ornith15-radeon-ai-pro-r9700",[1384,1814,1711,1769,1815,1816,1770,1771,1772,1817],"Kunstmatige intelligentie","GPU-prestaties","Inferentielatentie","Kostenefficiëntie",{"path":1819,"title":1820,"description":1821,"date":1822,"slug":1823,"image":1824,"originalUrl":1825,"categories":1826},"\u002Fblog\u002Fpaiton-qwen38-radeon-ai-pro-r9700","Paiton: 21% meer Qwen3.8-doorvoer op Radeon AI PRO R9700","Paiton draait AMD's Qwen3.8 27B op één Radeon AI PRO R9700 met 39,77 outputtokens per seconde. Dat levert 21% meer throughput en 17,4% lagere gemodelleerde kosten op.","2026-09-04T09:00:00","paiton-qwen38-radeon-ai-pro-r9700","\u002Fasset\u002Fimages\u002Fblog\u002Fpaiton-r9700\u002F00-featured-paiton-r9700.webp","https:\u002F\u002Feliovp.com\u002Fblog\u002Fpaiton-qwen38-radeon-ai-pro-r9700",[1384,1814,1711,1769,1815,1816,1770,1771,1772,1817],{"path":1828,"title":1829,"description":1830,"date":1831,"slug":1832,"image":1833,"originalUrl":1727,"categories":1834},"\u002Fblog\u002Fai-data-center-power-requirements-gpu-per-megawatt","Stroomvereisten voor AI-datacenters: de GPU-per-MW-illusie","Waarom verschillen GPU-aantallen per megawatt? Lees hoe PUE, piekbelasting, opslag, netwerken en koeling de inzetbare AI-capaciteit bepalen.","2026-07-27T23:52:00","ai-data-center-power-requirements-gpu-per-megawatt","\u002Fasset\u002Fimages\u002Fblog\u002Fai-data-center-power-requirements-gpu-per-megawatt\u002Fgpu-per-megawatt-illusion.webp",[1835,1836,1837,1838,1839,1840],"Alle","AI-infrastructuur","Datacenters","ModFlex","HPC","AMD Helios",{"path":1842,"title":1843,"description":1844,"date":1845,"slug":1846,"image":1847,"originalUrl":1848,"categories":1849},"\u002Fblog\u002Fpaiton-returns-to-its-diffusion-roots-optimizing-wan2-2-t2v-a14b-on-amd-mi355x","Wan2.2-videogeneratie: Paiton op AMD MI355X","Vergelijk Wan2.2-videogeneratie op AMD MI355X met Paiton en NVIDIA B200 via Diffusers. Lees hoe we diffusiemodellen optimaliseren.","2026-06-10T14:04:04","paiton-returns-to-its-diffusion-roots-optimizing-wan2-2-t2v-a14b-on-amd-mi355x","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fpaitonwan2.webp","https:\u002F\u002Feliovp.com\u002Fpaiton-returns-to-its-diffusion-roots-optimizing-wan2-2-t2v-a14b-on-amd-mi355x\u002F",[1835,1814,1384,1850,1851,1852,1853,1854,1855,1856,1857,1858,1859,1860,1861,1862,1863,1864,1865,1866,1384,1867,1868,1869,1870,1871,1872],"14B","AMD","B200","Benchmarks","Blackwell","Compute","Diffusie","Eliovp","Generatieve AI","GPU","Hardware","Inferentie","Instinct","MI355x","NVIDIA","On-premises","Optimalisatie","Soevereine AI","T2V","Tekst-naar-video","Tuning","Video-generatie","Wan2.2",{"path":1874,"title":1875,"description":1876,"date":1877,"slug":1878,"image":1879,"originalUrl":1880,"categories":1881},"\u002Fblog\u002Ffrom-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure","ElioVP in De Tijd: chipoptimalisatie en datacenters","Lees hoe De Tijd ElioVP belicht, van de oorsprong in chipoptimalisatie tot het werk aan modulaire datacenters en koeling voor hoge vermogensdichtheid.","2026-02-10T20:48:12","from-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fphysicalnewspaper.webp","https:\u002F\u002Feliovp.com\u002Ffrom-the-attic-to-the-front-page-eliovp-recognized-as-a-pioneer-in-chip-optimization-data-center-infrastructure\u002F",[1835,1814,1882,1883,1851,1884,1882,1864],"Modulaire DC","Niet gecategoriseerd","De Tijd",{"path":1886,"title":1887,"description":1888,"date":1889,"slug":1890,"image":1891,"originalUrl":1892,"categories":1893},"\u002Fblog\u002Fprivacy-is-geen-it-probleem-meer-het-is-een-strategische-prioriteit","AI en privacy: een strategische prioriteit in de Benelux","Privacyrisico's van generatieve AI, vertrouwen, dataopslag en governance. Waarom bedrijven in de Benelux veilige AI strategisch moeten benaderen.","2026-01-29T13:51:11","privacy-is-geen-it-probleem-meer-het-is-een-strategische-prioriteit","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fheaderimage.webp","https:\u002F\u002Feliovp.com\u002Fprivacy-is-geen-it-probleem-meer-het-is-een-strategische-prioriteit\u002F",[1835,1814,1894,1883,1895,1896,1897,1898,1899,1900,1901,1902,1857,1903,1858,1904,1905,1906],"Trending","AI Act","Antropomorfisme","AVG","Benelux","ChatGPT","Cyberbeveiliging","Databeheer","Gegevensbeveiliging","GDPR","Microsoft Copilot","Privacy","Shadow AI",{"path":1908,"title":1909,"description":1910,"date":1911,"slug":1912,"image":1913,"originalUrl":1914,"categories":1915},"\u002Fblog\u002Fitsme-bij-ons-is-het-its-not-me-en-dit-is-waarom","Waarom wij itsme niet gebruiken: privacy en soevereiniteit","Waarom ElioVP itsme niet gebruikt: onze afwegingen rond identiteitsmetadata, cloudafhankelijkheid, privacy en datasoevereiniteit.","2025-11-27T09:32:14","itsme-bij-ons-is-het-its-not-me-en-dit-is-waarom","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Ffrontimage.webp","https:\u002F\u002Feliovp.com\u002Fitsme-bij-ons-is-het-its-not-me-en-dit-is-waarom\u002F",[1835,1916,1917,1918,1900,1919,1920,1921,1903,1922,1923,1924,1905],"AWS","Belgian Mobile ID","CLOUD Act","Datasoevereiniteit","Digitale identiteit","eIDAS","itsme","Liberty Global","MyGov.be",{"path":1926,"title":1927,"description":1928,"date":1929,"slug":1930,"image":1931,"originalUrl":1932,"categories":1933},"\u002Fblog\u002Ffield-report-the-reality-of-building-agentic-ai-in-2025","Praktijkrapport: de realiteit van Agentic AI bouwen in 2025","Praktijklessen over lokale AI-agents in 2025 gaan in op workflowontwerp, observability, modeltraining, hallucinaties en GPU-geheugenlimieten.","2025-11-25T14:03:39","field-report-the-reality-of-building-agentic-ai-in-2025","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Ffieldreport.webp","https:\u002F\u002Feliovp.com\u002Ffield-report-the-reality-of-building-agentic-ai-in-2025\u002F",[1835,1814,1934,1894,1935,1936,1937,1938,1939,1940,1941,1942,1867,1943],"Oplossingen","Agentic AI","AI-techniek","AI-strategie","Autonome agenten","Bedrijfs-AI","Lokale LLM","Modelverfijning","AI op locatie","VRAM-optimalisatie",{"path":1945,"title":1946,"description":1947,"date":1948,"slug":1949,"image":1950,"originalUrl":1951,"categories":1952},"\u002Fblog\u002Fthe-synthetic-unicorn-bubble","De synthetische unicornzeepbel","Een analyse van investeringsrisico’s bij AI-neoclouds: circulaire financiering, infrastructuurclaims, contractvoorwaarden en due diligence.","2025-11-24T19:22:28","the-synthetic-unicorn-bubble","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fsyntheticunicorn.webp","https:\u002F\u002Feliovp.com\u002Fthe-synthetic-unicorn-bubble\u002F",[1835,1814,1894,1953,1954,1955,1956,1957,1958,1959,1960,1961,1962],"AI Infrastructure","AI Neocloud","Circulaire financiering","GPU Cloud","Beleggingsrisico's","Opstartwaardering","Synthetische bubbel","Technische analyse","Vaporware","Durfkapitaal",{"path":1964,"title":1965,"description":1966,"date":1967,"slug":1968,"image":1969,"originalUrl":1970,"categories":1971},"\u002Fblog\u002Fbuilding-the-engine-for-the-ai-race-the-4-month-path-to-nvidia-gb300-nvl72-power","NVIDIA GB300 NVL72: modulair datacenter in vier maanden","Ontdek een modulair datacenterontwerp voor NVIDIA GB300 NVL72, met redundante voeding, hybride koeling en een bouwplanning van vier maanden.","2025-11-20T14:10:19","building-the-engine-for-the-ai-race-the-4-month-path-to-nvidia-gb300-nvl72-power","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fsuperpodmodflexfrontimage.webp","https:\u002F\u002Feliovp.com\u002Fbuilding-the-engine-for-the-ai-race-the-4-month-path-to-nvidia-gb300-nvl72-power\u002F",[1835,1882,1883,1972,1836,1973,1974,1975,1976,1977,1978,1979,1980],"150 kW-rack","DLC","Hoge dichtheid","Vloeistofkoeling","Modulair datacenter","NVIDIA Blackwell Ultra","NVIDIA GB300","NVL72","Snelle implementatie",{"path":1982,"title":1983,"description":1984,"date":1985,"slug":1986,"image":1987,"originalUrl":1988,"categories":1989},"\u002Fblog\u002Fwhy-cuda-translation-wont-unlock-amds-real-potential","CUDA-vertaling versus AMD-gerichte optimalisatie","Waarom CUDA-compatibiliteit niet hetzelfde is als AMD-prestaties: over ROCm, HIP, kerneloptimalisatie en hardwaregerichte afstemming.","2025-11-12T14:48:37","why-cuda-translation-wont-unlock-amds-real-potential","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fchatgpt-image-nov-11-2025-09_16_10-pm-1.webp","https:\u002F\u002Feliovp.com\u002Fwhy-cuda-translation-wont-unlock-amds-real-potential\u002F",[1835,1814,1384,1883,1990,1814,1991,1992,1993,1994,1995,1996,1384,1997],"AMD MI300X","CUDA-vertaling","FP8","GPU-optimalisatie","High-performance computing","HIP","Kerneltuning","ROCm",{"path":1999,"title":2000,"description":2001,"date":2002,"slug":2003,"image":2004,"originalUrl":2005,"categories":2006},"\u002Fblog\u002Fpaiton-the-simplest-way-to-supercharge-ai-inference","Paiton: snellere AI-inferentie in uw bestaande stack","Lees hoe Paiton aansluit op bestaande inferentiestacks, met AMD MI300X-benchmarks en vergelijkingen van prestaties per dollar.","2025-11-11T10:31:22","paiton-the-simplest-way-to-supercharge-ai-inference","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fpaiton-powaaah.webp","https:\u002F\u002Feliovp.com\u002Fpaiton-the-simplest-way-to-supercharge-ai-inference\u002F",[1835,1814,1384,1769,2007,1990,1817,2008,1770,1996,1384,2009,1772],"AMD Instinct","Hoge throughput","SGLang",{"path":2011,"title":2012,"description":2013,"date":2014,"slug":2015,"image":2016,"originalUrl":2017,"categories":2018},"\u002Fblog\u002Fstop-overpaying-paiton-mi300x-moe-beats-h200-b200-on-1m-tokens","Paiton MoE-benchmarks: MI300X versus H200 en B200","Vergelijk Qwen3-30B-A3B MoE-benchmarks van MI300X met Paiton, H200 en B200: throughput en kosten per miljoen tokens.","2025-09-26T13:36:18","stop-overpaying-paiton-mi300x-moe-beats-h200-b200-on-1m-tokens","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fhulkvshulkpaitonwins.webp","https:\u002F\u002Feliovp.com\u002Fstop-overpaying-paiton-mi300x-moe-beats-h200-b200-on-1m-tokens\u002F",[1835,1814,1384,2019,1990,2020,1770,2021,2022,2023,2024,1384,2025],"AI-benchmarks","Kosten per token","Mixture of Experts","MoE","NVIDIA B200","NVIDIA H200","Qwen3",{"path":2027,"title":2028,"description":2029,"date":2030,"slug":2031,"image":2032,"originalUrl":2033,"categories":2034},"\u002Fblog\u002Fagentic-ai-but-make-it-local-from-inbox-to-insight-to-action-en","Lokale Agentic AI: van inbox naar actie","Lokale AI-agents zetten e-mails, documenten en beelden om in tickets, rapporten en acties, met modellen op maat van uw gegevens en systemen.","2025-09-16T13:09:00","agentic-ai-but-make-it-local-from-inbox-to-insight-to-action-en","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Ffrontfotoblog.webp","https:\u002F\u002Feliovp.com\u002Fagentic-ai-but-make-it-local-from-inbox-to-insight-to-action-en\u002F",[1835,1814,1934,1883,1935,2035,2036,2037,2038,1940,1942,1867,2039,2040],"Schadedetectie","Documentverwerking","E-mailautomatisering","Factuurextractie","Ticketautomatisering","Workflowautomatisering",{"path":2042,"title":2043,"description":2044,"date":2045,"slug":2046,"image":2047,"originalUrl":2048,"categories":2049},"\u002Fblog\u002Fmi300x-fp8-data-parallel-benchmarks-8-64-gpus-h200-left-behind-b200-within-reach","MI300X FP8-benchmarks: GPU-partitionering met Paiton","Bekijk hoe Paiton presteert met Llama 3.1 8B FP8 op gepartitioneerde MI300X-GPU's, vergeleken met NVIDIA H200 en B200.","2025-07-31T13:32:57","mi300x-fp8-data-parallel-benchmarks-8-64-gpus-h200-left-behind-b200-within-reach","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fimage-2-1.webp","https:\u002F\u002Feliovp.com\u002Fmi300x-fp8-data%e2%80%91parallel-benchmarks-8-64-gpus-h200-left-behind-b200-within-reach\u002F",[1835,1814,1384,1883,2050,1851,1852,2051,2052,1863,1864,1384,1772],"AI","H200","MI300X",{"path":2054,"title":2055,"description":2056,"date":2057,"slug":2058,"image":2059,"originalUrl":2060,"categories":2061},"\u002Fblog\u002Fapplicable-ai-for-businesses","Toepasbare AI voor bedrijven","Ontdek hoe ElioVP lokale AI voor bedrijfsprocessen bouwt, met modeltraining op maat en automatische schadedetectie voor de logistiek.","2025-07-09T21:35:30","applicable-ai-for-businesses","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fscherm_afbeelding-2025-07-09-om-23.30.17.webp","https:\u002F\u002Feliovp.com\u002Fapplicable-ai-for-businesses\u002F",[1835,1814,1934,1935,2035,2036,2037,2038,1940,1942,1867,2039,2040],{"path":2063,"title":2064,"description":2065,"date":2066,"slug":2067,"image":31,"originalUrl":2068,"categories":2069},"\u002Fblog\u002Fintroducing-paitons-free-evaluation-models","Maak kennis met de gratis evaluatiemodellen van Paiton","Test Paiton met gratis evaluatiemodellen voor AMD-GPU's. Vergelijk de prestaties voor tekst, beeldanalyse en beeldgeneratie met uw eigen workloads.","2025-07-07T11:26:13","introducing-paitons-free-evaluation-models","https:\u002F\u002Feliovp.com\u002Fintroducing-paitons-free-evaluation-models\u002F",[1835,1814,1384],{"path":2071,"title":2072,"description":2073,"date":2074,"slug":2075,"image":2076,"originalUrl":2077,"categories":2078},"\u002Fblog\u002Fpaiton-dramatically-faster-startup-and-performance-for-llama-3-1-405b","Llama 3.1 405B: sneller starten met Paiton op MI300X","Bekijk Paiton-benchmarks voor Llama 3.1 405B op acht AMD MI300X-GPU's, met opstarttijd, tensorparallelisme, throughput en latency.","2025-06-12T20:15:23","paiton-dramatically-faster-startup-and-performance-for-llama-3-1-405b","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fservingscreenshot.webp","https:\u002F\u002Feliovp.com\u002Fpaiton-dramatically-faster-startup-and-performance-for-llama-3-1-405b\u002F",[1835,1814,1384,1883,1769,1990,2079,1992,2080,2081,2082,1384,2083,2084],"Koude start","Grafiekcompilatie","Llama 3.1 405B","LLM-optimalisatie","Opstartlatentie","Tensor-parallellisme",{"path":2086,"title":2087,"description":2088,"date":2089,"slug":2090,"image":2091,"originalUrl":2092,"categories":2093},"\u002Fblog\u002Fpaiton-fp8-beats-nvidias-h200-on-amds-mi300x","Paiton FP8 verslaat NVIDIA's H200 op AMD's MI300X","Vergelijk Paiton op AMD MI300X met NVIDIA H200 voor Llama 3.1 70B FP8: throughput, wachttijd tot het eerste token en latency bij diverse batchgroottes.","2025-06-08T19:12:40","paiton-fp8-beats-nvidias-h200-on-amds-mi300x","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fblognewfp8.webp","https:\u002F\u002Feliovp.com\u002Fpaiton-fp8-beats-nvidias-h200-on-amds-mi300x\u002F",[1835,1814,1384,1883,1990,2094,1939,1858,1815,1816,1771,2081,2095,2096],"Koude startoptimalisatie","Model serving","vLLM-optimalisatie",{"path":2098,"title":2099,"description":2100,"date":2101,"slug":2102,"image":2103,"originalUrl":2104,"categories":2105},"\u002Fblog\u002Fmi300x-vs-h200-vs-rx-7900-xtx-vs-tenstorrent-n300s-with-vllm","MI300X, H200, RX 7900 XTX en n300s: vLLM-benchmarks","Vergelijk MI300X, H200, RX 7900 XTX en Tenstorrent n300s met vLLM: throughput, gemodelleerde tokenkosten en hardwarebeperkingen voor Llama 3 8B.","2025-05-09T14:03:58","mi300x-vs-h200-vs-rx-7900-xtx-vs-tenstorrent-n300s-with-vllm","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fcomparisontenstor.webp","https:\u002F\u002Feliovp.com\u002Fmi300x-vs-h200-vs-rx-7900-xtx-vs-tenstorrent-n300s-with-vllm\u002F",[1835,1814,1384,1934,1883,1851,2052,1864,2106,2107],"RX7900XTX","tenstorrent",{"path":2109,"title":2110,"description":2111,"date":2112,"slug":2113,"image":2114,"originalUrl":2115,"categories":2116},"\u002Fblog\u002Fclusterpl-empowering-gpu-cluster-investors-with-real-world-financial-insights","ClusterP&L: financiële modellen voor GPU-clusters","Ontdek hoe ClusterP&L kosten, rendement en investeringsscenario's voor GPU-clusters modelleert, met risicoanalyses en exporteerbare rapporten.","2025-05-03T10:52:22","clusterpl-empowering-gpu-cluster-investors-with-real-world-financial-insights","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fcomparisonscenarios.webp","https:\u002F\u002Feliovp.com\u002Fclusterpl-empowering-gpu-cluster-investors-with-real-world-financial-insights\u002F",[1835,1814,1882,1934,1852,2051,2117,1864,2118],"MI325X","P&L-calculator",{"path":2120,"title":2121,"description":2122,"date":2123,"slug":2124,"image":2125,"originalUrl":2126,"categories":2127},"\u002Fblog\u002Fcranking-out-faster-tokens-for-fewer-dollars-amd-mi300x-vs-nvidia-h200","AMD MI300X versus NVIDIA H200: Qwen3-32B met Paiton","Vergelijk Qwen3-32B-benchmarks op AMD MI300X met Paiton en NVIDIA H200, met resultaten voor throughput, latency en hardwarekosten.","2025-05-02T21:10:30","cranking-out-faster-tokens-for-fewer-dollars-amd-mi300x-vs-nvidia-h200","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002F3ac59a73-2466-4422-b7e5-ef2e4a8ca58e.webp","https:\u002F\u002Feliovp.com\u002Fcranking-out-faster-tokens-for-fewer-dollars-amd-mi300x-vs-nvidia-h200\u002F",[1835,1814,1384,2050,1851,2051,2128,1864,1384,1772],"MI300",{"path":2130,"title":2131,"description":2132,"date":2133,"slug":2134,"image":2135,"originalUrl":2136,"categories":2137},"\u002Fblog\u002Fpower-meets-precision-high-density-modular-data-center-for-nvidia-nvl-deployments-1-2-mw","Modulaire datacenters voor NVIDIA NVL: 1 tot 2 MW","Ontdek modulaire datacenterontwerpen voor NVIDIA NVL-systemen, met aandacht voor vermogen, vloeistofkoeling, redundantie en uitrolplanning.","2025-05-02T14:09:59","power-meets-precision-high-density-modular-data-center-for-nvidia-nvl-deployments-1-2-mw","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Feliovp_critical-1mw-pod_rev-2_transparent.webp","https:\u002F\u002Feliovp.com\u002Fpower-meets-precision-high-density-modular-data-center-for-nvidia-nvl-deployments-1-2-mw\u002F",[1835,1882,2138,1953,1974,1839,1975,1976,2139,2140,1979,2141],"1-2MW datacenter","NVIDIA Blackwell","NVIDIA NVL","Precisiekoeling",{"path":2143,"title":2144,"description":2145,"date":2146,"slug":2147,"image":2148,"originalUrl":2149,"categories":2150},"\u002Fblog\u002Fexamining-ai-agents-in-the-medical-field-ai-that-speaks-dicom","AI-agents in de medische wereld: AI die DICOM spreekt","Ontdek een lokale AI-agent die DICOM-gegevens opzoekt en bekijk tests van beeldmodellen met geanonimiseerde medische beelden.","2025-04-11T14:45:48","examining-ai-agents-in-the-medical-field-ai-that-speaks-dicom","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fhealthcareblog-1.webp","https:\u002F\u002Feliovp.com\u002Fexamining-ai-agents-in-the-medical-field-ai-that-speaks-dicom\u002F",[1835,1814,1934,1883,2050,1851,2151],"Zorg",{"path":2153,"title":2154,"description":2155,"date":2156,"slug":2157,"image":2158,"originalUrl":2159,"categories":2160},"\u002Fblog\u002Feliovp-bv-your-trusted-partner-for-supply-chain-resilience-amidst-new-u-s-tariffs","Amerikaanse invoerheffingen en AI-leveringszekerheid in 2025","Lees ElioVP's visie uit april 2025 op Amerikaanse invoerheffingen en leveringszekerheid voor AI-servers, HPC-systemen en modulaire datacenters.","2025-04-04T10:01:27","eliovp-bv-your-trusted-partner-for-supply-chain-resilience-amidst-new-u-s-tariffs","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Ftariffsshipping.webp","https:\u002F\u002Feliovp.com\u002Feliovp-bv-your-trusted-partner-for-supply-chain-resilience-amidst-new-u-s-tariffs\u002F",[1835,1894,2050,1851,2161,2162,2163,2164],"Invoer","Taiwan","Invoerheffingen","Trump",{"path":2166,"title":2167,"description":2168,"date":2169,"slug":2170,"image":2171,"originalUrl":2172,"categories":2173},"\u002Fblog\u002Fwhy-ai-agents-are-the-future","Waarom AI-agenten de toekomst zijn","Ontdek AI-agents voor ERP, CRM, financiën en klantondersteuning, met praktijkvoorbeelden en een traject van procesanalyse tot pilot en uitrol.","2025-03-23T22:06:59","why-ai-agents-are-the-future","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Ferp2.jpeg","https:\u002F\u002Feliovp.com\u002Fwhy-ai-agents-are-the-future\u002F",[1835,1814,1934,2050,2174,2175],"AI-agenten","ERP",{"path":2177,"title":2178,"description":2179,"date":2180,"slug":2181,"image":2182,"originalUrl":2183,"categories":2184},"\u002Fblog\u002Fthe-rise-of-open-source-ai-model-optimization","De opkomst van open-source AI-modeloptimalisatie","Verken trends in opensource-AI-optimalisatie: kwantisatie, mixture-of-experts-modellen, hardwaregerichte afstemming, RAG en edge-AI.","2025-03-22T20:59:23","the-rise-of-open-source-ai-model-optimization","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Friseofopensource.jpeg","https:\u002F\u002Feliovp.com\u002Fthe-rise-of-open-source-ai-model-optimization\u002F",[1835,1814,1894,2185,1851,1859,1864],"AI-nieuws",{"path":2187,"title":2188,"description":2189,"date":2190,"slug":2191,"image":2192,"originalUrl":2193,"categories":2194},"\u002Fblog\u002Fintroducing-our-benchmarking-tool-powered-by-dstack","Maak kennis met onze benchmarktool, gebouwd op dstack","Ontdek onze benchmarktool met dstack: herhaalbare vLLM-tests, automatische parameterreeksen en prestatierapporten voor lokale GPU's en de cloud.","2025-03-20T14:21:59","introducing-our-benchmarking-tool-powered-by-dstack","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fbenchmarktool.jpeg","https:\u002F\u002Feliovp.com\u002Fintroducing-our-benchmarking-tool-powered-by-dstack\u002F",[1835,1814,1384,2050,1851,2195,2196,2052,1384],"benchmark","LLM",{"path":2198,"title":2199,"description":2200,"date":2201,"slug":2202,"image":2203,"originalUrl":2204,"categories":2205},"\u002Fblog\u002Foptimizing-qwq-32b-by-qwen-amd-mi300x-vs-nvidia-h200","QwQ-32B optimaliseren (door Qwen): AMD MI300X versus NVIDIA H200","Vergelijk throughput en latency van QwQ-32B op AMD MI300X met Paiton en NVIDIA H200, bij kleine batches en meer gelijktijdige aanvragen.","2025-03-19T21:41:44","optimizing-qwq-32b-by-qwen-amd-mi300x-vs-nvidia-h200","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fpaiton4.jpeg","https:\u002F\u002Feliovp.com\u002Foptimizing-qwq-32b-by-qwen-amd-mi300x-vs-nvidia-h200\u002F",[1835,1814,1384],{"path":2207,"title":2208,"description":2209,"date":2210,"slug":2211,"image":2212,"originalUrl":2213,"categories":2214},"\u002Fblog\u002Feliovp-featured-on-amd-tech-talk-podcast","Eliovp te gast in de AMD Tech Talk-podcast","Beluister Elio Van Puyvelde en Jim Greene in de AMD Tech Talk-podcast over het ontstaan van ElioVP en de hardware- en softwarediensten voor AI.","2025-03-19T07:53:39","eliovp-featured-on-amd-tech-talk-podcast","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Ftechtalkjimgreene.jpeg","https:\u002F\u002Feliovp.com\u002Feliovp-featured-on-amd-tech-talk-podcast\u002F",[1835,1851,2215,2216,2217],"Jim Greene","Podcast","Tech Talk",{"path":2219,"title":2220,"description":2221,"date":2222,"slug":2223,"image":2224,"originalUrl":2225,"categories":2226},"\u002Fblog\u002Ffurther-optimizing-amd-powered-inference-with-paiton","AMD-inferentie verder optimaliseren met Paiton","Bekijk Paiton-benchmarks voor DeepSeek R1 Distill Llama 8B op AMD MI300X, gericht op throughput en latency bij kleinere batchgroottes.","2025-03-13T06:18:30","further-optimizing-amd-powered-inference-with-paiton","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fpaitonpost3.webp","https:\u002F\u002Feliovp.com\u002Ffurther-optimizing-amd-powered-inference-with-paiton\u002F",[1835,1814,1384,1851,2227,2228,2051,2052,2117,1384,1772],"DeepSeek","H100",{"path":2230,"title":2231,"description":2232,"date":2233,"slug":2234,"image":2235,"originalUrl":2236,"categories":2237},"\u002Fblog\u002Fa-first-look-at-paiton-in-action-deepseek-r1-distill-llama-3-1-8b","Paiton-benchmarks: DeepSeek R1 Distill Llama 3.1 8B","Vergelijk standaard- en Paiton-versies van DeepSeek R1 Distill Llama 3.1 8B op AMD MI300X, met benchmarks voor throughput en latency.","2025-01-31T09:11:02","a-first-look-at-paiton-in-action-deepseek-r1-distill-llama-3-1-8b","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fpaitonpost2.webp","https:\u002F\u002Feliovp.com\u002Fa-first-look-at-paiton-in-action-deepseek-r1-distill-llama-3-1-8b\u002F",[1835,1814,1384,1851,2227,2228,2051,2052,2117,1384,1772],{"path":2239,"title":2240,"description":2241,"date":2242,"slug":2243,"image":2244,"originalUrl":2245,"categories":2246},"\u002Fblog\u002Fai-model-optimization-with-paiton","AI-modeloptimalisatie met Paiton","Lees hoe Paiton modelcompilatie, aangepaste kernels en kernelfusie inzet om AI-inferentie op AMD GPU's te optimaliseren.","2025-01-30T19:53:25","ai-model-optimization-with-paiton","\u002Fasset\u002Fimages\u002Fblog\u002Fimported\u002Fpaitonpost1.webp","https:\u002F\u002Feliovp.com\u002Fai-model-optimization-with-paiton\u002F",[1835,1814,1384,1851,2228,2051,2052,2117,1384,1772],1791835013876]