All categories Paiton (42) Artificial Intelligence (28) AMD (13) AMD Radeon (13) Local AI (10) vLLM (10) NVidia (7) Solutions (7) AI (6) AI Inference (6) H200 (6) MI300X (6) Modular DC (6) Quantization (6) Qwen (6) AI Infrastructure (5) AMD MI300X (5) Inference Optimization (5) Trending (5) AMD Instinct (4) MI325x (4) Sovereign AI (4) Agentic AI (3) B200 (3) Cost Efficiency (3) Generative AI (3) GPU Performance (3) H100 (3) Image Generation (3) Inference Latency (3) Large Language Models (3) Liquid Cooling (3) Local LLM (3) On-Premise AI (3) ComfyUI (2) Cybersecurity (2) Damage Detection (2) Deepseek (2) Document Processing (2) Eliovp (2) Email Automation (2) Enterprise AI (2) FP8 (2) GDPR (2) GPU (2) High Density (2) HPC (2) Inference (2) Invoice Extraction (2) Kernel Tuning (2) Llama 3.1 405B (2) MI355x (2) ModFlex (2) Modular Data Center (2) NVL72 (2) Privacy (2) Ticket Automation (2) Workflow Automation (2) 1-2MW Data Center (1) 14B (1) 150kW Rack (1) 3D Generation (1) AI Act (1) AI Agents (1) AI Benchmarks (1) AI Engineering (1) AI Neocloud (1) AI news (1) AI Strategy (1) AMD Helios (1) Anthropomorphism (1) Autonomous Agents (1) AVG (1) AWS (1) Belgian Mobile ID (1) benchmark (1) Benchmarks (1) Benelux (1) Blackwell (1) ChatGPT (1) Circular Financing (1) Cloud Act (1) Cold Start (1) Cold Start Optimization (1) Compute (1) Cost per Token (1) CUDA Translation (1) Data Centers (1) Data Governance (1) Data Security (1) Data Sovereignty (1) De Tijd (1) DeepSeek (1) DFlash2 (1) Diffusion (1) Digital Identity (1) DLC (1) eIDAS (1) ERP (1) FLUX (1) GGUF (1) GPU Cloud (1) GPU Optimization (1) Graph Compilation (1) Hardware (1) Healthcare (1) High Performance Computing (1) High Throughput (1) HIP (1) import (1) Instinct (1) Investment Risks (1) itsme (1) Jim Greene (1) Kimi (1) Liberty Global (1) LLM (1) LLM Optimization (1) MI300 (1) Microsoft Copilot (1) MiniMax (1) MiniMax H3 (1) Mixture of Experts (1) Model Fine-Tuning (1) Model Serving (1) MoE (1) MyGov.be (1) NVIDIA (1) NVIDIA B200 (1) NVIDIA Blackwell (1) NVIDIA Blackwell Ultra (1) NVIDIA GB300 (1) NVIDIA H200 (1) NVIDIA NVL (1) On-Premise (1) Optimization (1) pnl calculator (1) Podcast (1) Precision Cooling (1) Qwen3 (1) Qwen3.8 (1) Rapid Deployment (1) ROCm (1) RX7900XTX (1) SGLang (1) Shadow AI (1) Startup Latency (1) Startup Valuation (1) Synthetic Bubble (1) T2V (1) Taiwan (1) Tariffs (1) Tech Analysis (1) Tech Talk (1) Tensor Parallelism (1) tenstorrent (1) Text-to-Video (1) Trump (1) Tuning (1) Vaporware (1) Venture Capital (1) Vera Rubin (1) Video Generation (1) Video-Generation (1) vLLM Optimization (1) VRAM Optimization (1) Wan2.2 (1)
MiniMax-H3-Image on a single R9700 MiniMax-H3-Image on one Radeon AI PRO R9700: 2048 x 2048 in 6.9 seconds, 4096 x 4096 in 33.4 seconds. FP8 weights, image editing and setup.
By: ElioVP
November 12, 2026
Paiton
Kimi-K3.1-Pro on 6 MI355X GPUs at 800 W with Paiton Kimi-K3.1-Pro on six MI355X GPUs at 800 W each. Paiton throughput, power measurements, a separate 1M-context test and a four-GPU option.
By: ElioVP
November 11, 2026
Paiton
The Radeon AI PRO R9700 does 3D too: Idol in 16.4 seconds Idol turns an image into a 3D Gaussian splat in 16.44 seconds on one Radeon AI PRO R9700 with Paiton, versus 39.22 seconds for stock on the same GPU.
By: ElioVP
November 6, 2026
Paiton
Deepseek V4.1 Flash on a single MI350P DeepSeek V4.1 Flash on one 144 GB MI350P: 77.9 tokens/s for one request and 1,107.6 in a 512-request batch, with Paiton and CPU expert offload.
By: ElioVP
November 3, 2026
Paiton
Qwen3.8 Flash Next on MI350P: twice the speed | Paiton Qwen3.8 Flash Next on one AMD MI350P: 2.24× the tested vLLM setup's single-request decode speed and about 2.2 million shared KV-cache tokens with Paiton.
By: ElioVP
October 30, 2026
Paiton
