Live data from Hacker News

Qwen3-Next: Towards Ultimate Training and Inference Efficiency

Post reply on HN

Print view View original

1–2 of 2 posts

Qwen3-Next: Towards Ultimate Training and Inference Efficiency

#1

Post by bratao » Thu, Sep 11, 2025, 5:38 PM UTC

Qwen3-Next: Towards Ultimate Training and Inference Efficiency
qwen.ai

Re: Qwen3-Next: Towards Ultimate Training and Inference Efficiency

#2

Post by derac » Thu, Sep 11, 2025, 8:48 PM UTC

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.

Post reply on HN