Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All

Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All by 3836293648 on Thursday April 16, 2026 @05:08PM (#47799524)

How much VRAM do you need for that?

[ Parent | on HN ]

Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All by seemaze on Thursday April 16, 2026 @06:59PM (#47800608)

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

[ Parent | on HN ]

Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All by mistercheese on Friday April 17, 2026 @12:13AM (#47802393)

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

[ Parent | on HN ]

Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All by seemaze on Sunday April 19, 2026 @10:11AM (#47824451)

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

[ Parent | on HN ]

Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All by canpan on Friday April 17, 2026 @03:05AM (#47803240)

Not OP, but I ran 122b successfully with normal RAM offloading. You dont need all that much VRAM, which is super expensive. I used 96gb ram + 16gb vram gpu. But it's not very fast in that setup, maybe 15 token per second. Still, you can give it a task and come back later and its done. (Disclaimer: I build that PC before stuff got expensive)

[ Parent | on HN ]

Re:Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All by jwitthuhn on Friday April 17, 2026 @07:26AM (#47804734)

128GB on a mac with unified memory. The model itself takes something like 110 of that and then I have ~16 left over to hold a reasonably sized context and 2 for the OS.

I do have a dedicated machine for it though because I can't run an IDE at the same time as that model.

[ Parent | on HN ]