Dark Hacker News
new
|
best
|
ask
|
show
|
jobs
Qwen3.8 Weights Released
(modelscope.cn)
31 points
by
apitman
14 days ago
| 4 comments
Qwen3.8 Weights Released | Dark Hacker News
throwfaraway4
14 days ago
|
next
[−]
https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B
13hours
14 days ago
|
next
[−]
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
14 days ago
|
parent
|
next
[−]
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
14 days ago
|
next
[−]
Next up:
https://modelscope.cn/models/Qwen/Qwen3.8-27B
Probably easier to run for everyone.