top | item 45214130 Qwen3-Next: Towards Ultimate Training and Inference Efficiency 16 points| bratao | 5 months ago |qwen.ai 1 comment order hn newest derac|5 months 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.
derac|5 months 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.
derac|5 months ago