Qwen3-Next: Towards Ultimate Training and Inference Efficiency | Hacker News

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

		Qwen3-Next: Towards Ultimate Training and Inference Efficiency (qwen.ai)
		16 points by bratao 4 months ago \| hide \| past \| favorite \| 1 comment

derac 4 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.

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