---
pipeline_tag: text-generation
base_model:
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
---
This is a MXFP4_MOE imatrix quantization of the model [NVIDIA-Nemotron-3-Nano-30B-A3B](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16), based on the imatrix from unsloth.

As this is not yet supported in the mainline llama.cpp yet, you'll need to compile a special merge of it from here in order to run it:  
https://github.com/ggml-org/llama.cpp/pull/18058