Qwen3-4B-Thinking-2507 .wasm

[vladbuinceanu]

Hi,

I was wondering if anyone has tried running Qwen3-4B-Thinking-2507 in WebLLM. From what I’ve seen, it now supports a 128k context window, which makes it sound quite interesting.

If yes, which .wasm WebAssembly binary did you use for this model ?

Thanks!

[mchaliadzinau]

It looks like you've already figured it out 🥇
https://huggingface.co/vladbuinceanu/Qwen3-4B-Thinking-2507-q4f32_1-MLC