[ddarolfi]

Qwen 4.6 36B? Do they mean Qwen3.6-35B-A3B?

[trvz]

Yes. The author is really sloppy if that wasn’t clear from the article.

[Johnny_Bonk]

So I have a RTX 3080 10GB VRAM which I've been using with Qwen2.5 Coder and Gemma 4 E2B. Im wondering what models you have tried with which quants.

[mikeatlas]

yes