majentik
/

gemma-4-E4B-RotorQuant-MLX-4bit

Image-Text-to-Text

kv-cache-quantization

4-bit precision

Model card Files Files and versions

gemma-4-E4B-RotorQuant-MLX-4bit

Commit History

Add MLX quantized model with KV cache compression

f1e16a4
verified

majentik commited on 3 days ago

initial commit

f587fae
verified

majentik commited on 3 days ago