I squeeze Qwen3.5-122B-A10B at Q6 into 128GB. It's a great model. | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

seemaze 86 days ago | parent | context | favorite | on: Qwen3.6-35B-A3B: Agentic coding power, now open to...

I squeeze Qwen3.5-122B-A10B at Q6 into 128GB. It's a great model.

mistercheese 86 days ago [–]

Wow what kind of hardware do you have? Mac Studio, dgx spark, strix halo? How fast is it?

seemaze 84 days ago | [–]

Strix Halo, I'm seeing performance inline with these results[0].

I'm interested to investigate the claimed gains from the lemonade-sdk port of Apple MLX inference[1].

[0]https://kyuz0.github.io/amd-strix-halo-toolboxes/

[1]https://github.com/lemonade-sdk/lemonade/issues/1642

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact