HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Qwen3.8 Weights Released | Hacker News Reader
Qwen3.8 Weights Released
modelscope.cn
31 points
·
apitman
·
·
4 comments
Open article
Save
View on HN
throwfaraway4
·
https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B
13hours
·
Anyone know if a MoE model that can run on a gpu with 16GB VRAM (like 3.6-35B-A3B) is in the pipeline as well, or only the dense 27B one?
petu
·
Whoever runs their Twitter wouldn't confirm / promise anything beyond 27B, but didn't say no either. So maybe in a month, maybe not.
spwa4
·
Next up:
https://modelscope.cn/models/Qwen/Qwen3.8-27B
Probably easier to run for everyone.
Reply on news.ycombinator.com