Hugging Face's logo

ronantakizawa
/
molmo-72b-awq

Image-Text-to-Text
Transformers
Safetensors
English
molmo
text-generation
awq
quantized
4-bit precision
vision-language
qwen2
clip
llm-compressor
vllm
conversational
custom_code
compressed-tensors
Model card Files
xet
Community
molmo-72b-awq / processor_config.json

Commit History

Upload AWQ 4-bit quantized Molmo-72B (~37.8GB, 73.9% reduction)
3e87388
verified

ronantakizawa commited on