Hugging Face's logo

majentik
/
Leanstral-TurboQuant-MLX-2bit

MLX
Safetensors
mistral3
turboquant
kv-cache-quantization
2-bit
weight-quantization
leanstral
lean4
formal-proofs
theorem-proving
quantized
apple-silicon
mistral
Mixture of Experts
Model card Files
xet
 Community
Leanstral-TurboQuant-MLX-2bit

Commit History

Add MLX quantized model weights
9fbfbd1
verified

majentik commited on

Add model card (weights pending mlx_lm mistral3 architecture support)
642eaf9
verified

majentik commited on

initial commit
af6ecc8
verified

majentik commited on