Calling it a win because computer is stable with 3080 @ 200W, and Qwen 3.8 2-bit made it work
Awesome Demo!! I was able to point Qwen 3.8 27b at this GitHub repo and it was able to build a MASSIVE…
Awesome Demo!! I was able to point Qwen 3.8 27b at this GitHub repo and it was able to build a MASSIVE workflow to process each animation from a single image using MiniMax_AI H3 via ComfyUI ...took about 49 minutes on a 3090... Once finished I showed Qwen the screenshots of…
16G Beggars Edition M1 deployment Qwen 3.8-27B actual test report
No surprise, it’s like a typewriter, but my IQ is okay😄 📊 Measured configuration and data Device: MacBook Pro (M1/16GB) Model: Qwen3.8-27B (UD-Q2_K_XL, 9.15GB) GPU: Full layer Metal offloading Memory: Stable around 11 GB First Token delay: about 850ms Pre-filling speed: 10~12.5 tok/s…
Generated this 3D Pagoda Garden with Qwen 3.8 27B (Q4, low reasoning) running completely local on an RTX 3090.
Zero cloud APIs, full interactivity. 🏯🌸 ⛩️
You have reached the end of the archive
All of qwen38