Qwen 3.8 27B has arrived.
Load it into Msty Nexus and put it to work across your Msty ecosystem. Enrich Personas in Studio and power your Agents in Go. Powerful AI. Running local. 🔥
Guess what AI Model built this game?
Local Qwen 3.8 27B (NVFP4) via Hermes wrote a single-file HTML canvas Breakout. This model is straight fire 🔥
Tater Tot's Tetris - Escape The Dragon Edition 🔥
Made w/ Qwen 3.8 27B Q4 on 2x AMD 9060 XT GPU's (32 GB VRAM) - $500 GPU's. Took 3 hours w/ Hermes. 2625 lines of code, 59 tests, debugged itself in browser. 🤯 3 shot prompt.🚀 UnslothAI Alibaba_Qwen are legends!
Testing Qwen 3.8 from Alibaba_Qwen with 3sparks chat on my iPhone with the model running on my Framework desktop in lmstudio.
I’m getting 19-25tks on the Framework's AMD AI MAX 395 while on another PC with an AMD 7900XTX with 24 gigs of GPU mem, I’m getting around 30 tks.
You have reached the end of the archive
All of qwen38