Qwen3-Next: Towards Ultimate Training and Inference Efficiency (opens in new tab)

(qwen.ai)

16 pointsbratao6mo ago1 comments

1 comments

This seems very promising, they are matching Qwen3-235B-A22B-Instruct-2507. It should run on 8-12GB vram with 64 gb ram decently well.

j / k navigate · click thread line to collapse

(qwen.ai)

16 pointsbratao6mo ago1 comments

derac6mo ago

This seems very promising, they are matching Qwen3-235B-A22B-Instruct-2507. It should run on 8-12GB vram with 64 gb ram decently well.

j / k navigate · click thread line to collapse