1024m
/

Mistral-Small-Instruct-4bit-fp4

4-bit precision

Model card Files Files and versions

No model card

Downloads last month: 5

Safetensors

Model size

11.7B params

Tensor type

F32

·

BF16

·

U8

·

Inference Providers NEW

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