majentik
/

gemma-4-31B-it-RotorQuant-MLX-8bit

Image-Text-to-Text

kv-cache-quantization

8-bit precision

Model card Files Files and versions

gemma-4-31B-it-RotorQuant-MLX-8bit

Commit History

Add MLX quantized model with KV cache compression

d17bbcf
verified

majentik commited on 3 days ago

initial commit

3024c79
verified

majentik commited on 3 days ago