It is ALL local generated.
Yet another proof of concept. Don't judge it by the graphics quality/animation. Get what it is: I asked OMP+Qwen 3.8 Flash to generate html+css+js platformer frame - just movement, paralax, and idle/run/attack AND to generate all assets including
This is what a 180b model dancing looks like, qwen 3.8 flash next fp8 across 2x dgx spark, and the red boxes are the part that surprise me.
10 to 12 w per gpu at idle 30 to 35 w per gpu while it generates, peaks around 55 w never past 60°c on either box 45 tok/s fresh,
An RTX 3060 - the most common GPU on Steam just built an entire game with zero hand-written code.
Bonsai2, a Qwen 3.8 27B model, running on 12GB VRAM -5 hours, 328k tokens, 2,368 lines GPU sitting in local computers is now a local coding agent.
You have reached the end of the archive
All of qwen38