Llama-3.1-Nemotron-Nano-8B-v1 imatrix GGUF

This repository houses GGUF quants of the nvidia/Llama-3-1-Nemotron-Nano-8B-v1 repository, quantized with an imatrix based on the Tristan Druyen calibration data.

GGUF

Model size

8.03B params

Architecture

llama

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.