This is what you get with Qwen 3.8 Flash Next on Q4 from UnslothAI on a Mac M5 Max when you give it complex instruction as this
"can you make a beautiful html and js website with webgl on my desktop so that I can see show competent yoou are? - do a showoff " (with same exact
China just released an AI model that beat Anthropic's best.
It's free. It's open source. You can run it locally. And nobody in the US is talking about it: Alibaba's Qwen 3.8 Flash-Next. 125B parameters total. Only 6B active per token. It beat Claude Opus 4.6 Max on 8 out of
Atomic Chat HQ dropped a demo showing a 1-bit quantized Qwen 3.8 Flash Next model hitting 30 tokens per second on a consumer MacBook Pro M5 Max.
The media thought that was the story. It was not. The media thought the story was local hardware running consumer LLMs fast. It was
Voxel Pagoda Art done by Qwen 3.8 Flash
You have reached the end of the archive
All of qwen38