News for hackers. Stuff that matters.
Re:Qwen 3 now supports ARM and MLX by ukuina on Saturday September 13, 2025 @01:49AM (#45229663)
[June 2025]
Re:Qwen 3 now supports ARM and MLX by NiekvdMaas on Saturday September 13, 2025 @03:27AM (#45230068)
Re:Qwen 3 now supports ARM and MLX by littlestymaar on Saturday September 13, 2025 @03:50AM (#45230170)
The unfortunate thing with their Qwen3-next naming is that it doesn't reflect on the fact that the architecture is completely different from Qwen3. Much more different than the difference between Qwen2 and Qwen3 even.

So support is likely to take quite some time because it's not just regular transformer blocks stacked on each other, but a brand new hybrid architecture using SSM.

Re:Qwen 3 now supports ARM and MLX by NiekvdMaas on Saturday September 13, 2025 @03:58AM (#45230210)
From https://github.com/ggml-org/llama.cpp/issues/15940#issuecomm...:

> This is a massive task, likely 2-3 months of full-time work for a highly specialized engineer. Until the Qwen team contributes the implementation, there are no quick fixes.

Re:Qwen 3 now supports ARM and MLX by veber-alex on Saturday September 13, 2025 @04:25AM (#45230338)
It's already supported in vLLM, SGLang and MLX.
Re:Qwen 3 now supports ARM and MLX by littlestymaar on Saturday September 13, 2025 @06:44AM (#45231009)
The Qwen team made sure to land PRs to vLLM and SGLang on the first day, which is nice.
Re:Qwen 3 now supports ARM and MLX by p0w3n3d on Saturday September 13, 2025 @04:22AM (#45230326)
Yeah I've been using qwen3 on mlx in July already
Re:Qwen 3 now supports ARM and MLX by anemll on Sunday September 14, 2025 @07:55PM (#45244563)
It’s also supported in Apple Neural Engine https://github.com/Anemll/Anemll