xbill·Jun 2212B Gemma 4 Deployment with NVIDIA Blackwell 6000, MCP, Cloud Run, and Antigravity CLIThis article provides a step by step deployment guide for Gemma 4 to a Google Cloud Run hosted GPU enabled system,. A suite of Python MCP…
Allen Kuo (kwyshell)·Apr 18Qwen3.6–35B-A3B on Desktop Blackwell: The First Time vLLM Beats Ollama on DecodeThird in a series. Previous articles: Gemma 4 on vLLM vs Ollama · NVFP4 CompletionA response icon4A response icon4
Allen Kuo (kwyshell)·Apr 16Finishing What We Started: Gemma 4 NVFP4 on vLLM, Desktop Blackwell, WSL2A follow-up to Gemma 4 on vLLM vs Ollama: Benchmarks on a 96 GB Blackwell GPU.
Karim Gallimore·Apr 14The Architect Nobody Taught You AboutDavid Blackwell built the mathematics behind modern AI. The system tried to make sure you’d never know his name.
Allen Kuo (kwyshell)·Apr 8vLLM or Ollama on Blackwell? Benchmarks, Landmines, and What Agents Actually NeedI pushed an RTX PRO 6000 (96 GB) to its limits running both engines on Windows — crashed the system twice, discovered silent performance…
Beth Kindig·Mar 31Nvidia Stock Prediction: The Path to a $20 Trillion Market Cap is StrengtheningThis article was originally published on I/O Fund on March 27, 2026
Allen Kuo (kwyshell)·Mar 16InfiniteTalk Keeps Crashing Your GPU. Here’s Why — And My Open-Source FixComfyUI’s MultiTalk talking-head workflow triggers VIDEO_TDR_FAILURE on NVIDIA Blackwell GPUs. It took me some time to figure out why…
GeneLab·Mar 2Every ComfyUI Install Guide Failed on My RTX 5090 — So I Built My Own and Open-Sourced ItThree days of dependency hell on Windows led to a one-click setup that didn’t exist anywhere else.A response icon1A response icon1
InGoogle Cloud - CommunitybyKarl Weinmeister·Feb 25Serving Qwen 3.5 on Cloud Run with Blackwell GPUsCloud Run now supports NVIDIA RTX PRO 6000 Blackwell GPUs in preview. With 96GB of GDDR7 VRAM and 1.6 TB/s of memory bandwidth, it’s the…A response icon2A response icon2
