Hugging Face's logo

majentik
/
Leanstral-TurboQuant-MLX-4bit

MLX
Safetensors
mistral3
turboquant
kv-cache-quantization
4-bit precision
weight-quantization
leanstral
lean4
formal-proofs
theorem-proving
quantized
apple-silicon
mistral
Mixture of Experts
Model card Files
xet
 Community
Leanstral-TurboQuant-MLX-4bit

Commit History

Add MLX quantized model weights
0e86a72
verified

majentik commited on

Add model card (weights pending mlx_lm mistral3 support)
bb71737
verified

majentik commited on

initial commit
3442799
verified

majentik commited on