Hugging Face's logo

majentik
/
gemma-4-31B-it-RotorQuant-MLX-2bit

Image-Text-to-Text
MLX
Safetensors
gemma4
rotorquant
kv-cache-quantization
gemma
multimodal
quantized
2bit
conversational
2-bit
Model card Files
xet
 Community
gemma-4-31B-it-RotorQuant-MLX-2bit / processor_config.json

Commit History

Add MLX quantized model with KV cache compression
4c89218
verified

majentik commited on