The Model mlx-community/IBM-granite-3.2-2b-instruct-4bit was converted to MLX format from ibm-granite/granite-3.2-2b-instruct using mlx-lm version 0.21.3.

Downloads last month: 83

Safetensors

Model size

396M params

Tensor type

FP16

U32

Inference Providers NEW

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