majentik
/

gemma-4-26B-A4B-it-RotorQuant-MLX-4bit

Image-Text-to-Text

kv-cache-quantization

4-bit precision

Model card Files Files and versions

gemma-4-26B-A4B-it-RotorQuant-MLX-4bit

Commit History

chore(card): enrich YAML frontmatter (pipeline_tag, language, library_name, inference)

2f18d59
verified

majentik commited on 1 day ago

Add MLX quantized model with KV cache compression

4598a06
verified

majentik commited on 5 days ago

initial commit

24f96d6
verified

majentik commited on 5 days ago