ModelVerifiedExternal

Gemma 4 26B A4B It Qat OQ3 FP16

[!IMPORTANT] This quantization was uploaded on 2026-06-09 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights. gemma-4-26B-A4B-it-qat-oQ3-fp16

Verified source

Sourcehuggingface.co/avneetsb/gemma-4-26B-A4B-it-qat-oQ3-fp16

KindOtherVersionv1db507e27975668d7f4b828e5e0faf5c1f59f470Publisher@avneetsbCgrade

Model source

Kind: Other
Version: v1db507e27975668d7f4b828e5e0faf5c1f59f470
Publisher: @avneetsb
Parameters: 26B
Source: Hugging Face

Source description

--- library_name: mlx tags: - mlx - oq - quantized --- > [!IMPORTANT] > This quantization was uploaded on **2026-06-09** and replaces a previous version. > If you downloaded this model before this date, please re-download for the updated weights. # gemma-4-26B-A4B-it-qat-oQ3-fp16 This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.4.2) mixed-precision quantization. ## Quantization details - **Model type**: gemma4 - **Bits**: 3 - **Group size**: 64 - **Format**: MLX safetensors

Sources & provenance

1 active source

Hugging FaceRepresentative

huggingface.co/avneetsb/gemma-4-26B-A4B-it-qat-oQ3-fp16

highest_eligible_score

Verified Jul 11

Source evidence

3 excerpts

Readme excerptJul 11huggingface.co/avneetsb/gemma-4-26B-A4B-it-qat-oQ3-fp16

libraryname: mlx tags: mlx oq quantized

SummaryJul 11huggingface.co/avneetsb/gemma-4-26B-A4B-it-qat-oQ3-fp16