I built something like this just last month, using a few of the same models, but I used ThreeJS's Three-Shading-Language abstraction to do it: <a href="https://three-llm.ben3d.ca/?model=qwen3.5-0.8b" rel="nofollow">https://three-llm.ben3d.ca/?model=qwen3.5-0.8b
Awesome! I tried it and after loading (which took a while as it is a large model) got 12 tokens/second and very coherent output. Great demonstration.
bhouston · · focus · HN ↗
logicallee · · focus · HN ↗