ModelVerifiedExternal

NVIDIA Nemotron 3 Nano 4B OQ3.5 FP16

[!IMPORTANT] This quantization was uploaded on 2026-05-05 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights. NVIDIA-Nemotron-3-Nano-4B-oQ3.5-fp16

Verified source

Sourcehuggingface.co/avneetsb/NVIDIA-Nemotron-3-Nano-4B-oQ3.5-fp16

KindOtherVersionv2529f811aa4f7d3877e45638514e42b35be329e8Publisher@avneetsbCgrade

Model source

Kind: Other
Version: v2529f811aa4f7d3877e45638514e42b35be329e8
Publisher: @avneetsb
Parameters: 4B
Source: Hugging Face

Source description

--- library_name: mlx tags: - mlx - oq - quantized --- > [!IMPORTANT] > This quantization was uploaded on **2026-05-05** and replaces a previous version. > If you downloaded this model before this date, please re-download for the updated weights. # NVIDIA-Nemotron-3-Nano-4B-oQ3.5-fp16 This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.3.8) mixed-precision quantization. ## Quantization details - **Model type**: nemotron_h - **Bits**: 3 - **Group size**: 64 - **Format**: MLX safetensors

Sources & provenance

1 active source

Hugging FaceRepresentative

huggingface.co/avneetsb/NVIDIA-Nemotron-3-Nano-4B-oQ3.5-fp16

highest_eligible_score

Verified Jul 11

Source evidence

3 excerpts

Readme excerptJul 11huggingface.co/avneetsb/NVIDIA-Nemotron-3-Nano-4B-oQ3.5-fp16

libraryname: mlx tags: mlx oq quantized

SummaryJul 11huggingface.co/avneetsb/NVIDIA-Nemotron-3-Nano-4B-oQ3.5-fp16