Lowkey-Loki
/

Codestral-22b-v0.1-mlx-3_6bit

4-bit precision

Model card Files Files and versions

Quantized 3_6bit MLX version of https://huggingface.co/mistralai/Codestral-22B-v0.1 that performs better than regular 3bit MLX quants with a slightly larger size. Converted using mlx-lm 0.22.2

Downloads last month: 80

Safetensors

Model size

3B params

Tensor type

F16

·

U32

·

MLX

Hardware compatibility

Log In to add your hardware

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Lowkey-Loki/Codestral-22b-v0.1-mlx-3_6bit

Base model

mistralai/Codestral-22B-v0.1

Quantized

(51)

this model