Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Qwen
/
Qwen3-Coder-480B-A35B-Instruct-FP8
like
103
Follow
Qwen
45.3k
Text Generation
Transformers
Safetensors
qwen3_moe
conversational
fp8
arxiv:
2505.09388
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
8
Train
Deploy
Use this model
H20启动FP8失败
#3
by
darvec
- opened
22 days ago
Discussion
darvec
22 days ago
4张H20可以启动Qwen3-Coder-480B-A35B-Instruct-FP8吗，显存比模型小，但是MOE好像不需要占用全部显存？
See translation
Edit
Preview
Upload images, audio, and videos by dragging in the text input, pasting, or
clicking here
.
Tap or paste here to upload images
Comment
·
Sign up
or
log in
to comment
