Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
NVFP4
/
Qwen3-30B-A3B-Thinking-2507-FP4
like
4
Follow
NVFP4
114
Text Generation
Safetensors
Model Optimizer
qwen3_moe
nvidia
ModelOpt
Qwen3
quantized
FP4
conversational
8-bit precision
arxiv:
2505.09388
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
3
New discussion
New pull request
Resources
PR & discussions documentation
Code of Conduct
Hub documentation
All
Discussions
Pull requests
View closed (1)
Sort: Recently created
Weight dimension mismatch
#3 opened 6 days ago by
felt-mx
Update config.json
#2 opened 3 months ago by
prudant