Hugging Face's logo

cloudnathan5
/
Muse-Glimmer-30B-NVFP4

Image-Text-to-Text
Safetensors
vllm
muse_glimmer
nvfp4
fp4
compressed-tensors
llm-compressor
quantized
blackwell
multimodal
conversational
8-bit precision
Model card Files
xet
 Community
Muse-Glimmer-30B-NVFP4 / tokenizer.json

Commit History

Replace W4A4 with NVFP4A16: faster (74.7 vs 54.3 tok/s) and better PPL (5.5965 vs 5.7660)
05fb253
verified

cloudnathan5 commited on

Upload folder using huggingface_hub
3392d1d
verified

cloudnathan5 commited on