This is a MXFP4_MOE imatrix quantization of the model NVIDIA-Nemotron-3-Nano-30B-A3B, based on the imatrix from unsloth.

Get the latest llama.cpp in order to run it.

Also see the instructions here: Unsloth NVIDIA Nemotron 3 Nano - How To Run Guide

Downloads last month
2,316
GGUF
Model size
32B params
Architecture
nemotron_h_moe
Hardware compatibility
Log In to view the estimation

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF

Quantized
(13)
this model