majentik
/

Leanstral-RotorQuant-MLX-2bit

kv-cache-quantization

weight-quantization

theorem-proving

Mixture of Experts

Model card Files Files and versions

Leanstral-RotorQuant-MLX-2bit

Commit History

docs: Tier 2 polish — variant matrix + quant trade-off

9bd62b3
verified

majentik commited on 25 days ago

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

cd06d72
verified

majentik commited on Apr 17

Add MLX quantized model weights

b85864d
verified

majentik commited on Apr 13

Add model card (weights pending mlx_lm mistral3 architecture support)

137d154
verified

majentik commited on Apr 13

initial commit

c00cf09
verified

majentik commited on Apr 13