isogen
/

Mistral-Nemo-Instruct-2407-exl3-4bpw

4-bit precision

Model card Files Files and versions

EXL3 quantization of Mistral-Nemo-Instruct-2407, 4 bits per weight.

Downloads last month: 2

Safetensors

Model size

3.65B params

Tensor type

FP16

·

I16

·

Inference Providers NEW

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