ModelVerifiedExternal

Qwopus3.5 4B Coder OQ3

This model was quantized using oQ (oMLX v0.4.4) mixed-precision quantization.

Sourcehuggingface.co/mlx-works/Qwopus3.5-4B-Coder-oQ3/tree/fce8edf59f46c91f98fcae6efb588d97069ae737

KindText modelVersionmodelPublisher@mlx-worksCgrade

Model source

Kind: Text model
File size: 2.50 GB
Version: vmodel
Updated: Oct 21, 2026
Publisher: @mlx-works
Downloads: 5
Parameters: 4B
Source: Hugging Face

Source description

Qwopus3.5-4B-Coder-oQ3

This model was quantized using oQ (oMLX v0.4.4) mixed-precision quantization.

Quantization details

Model type: qwen3_5
Bits: 3
Group size: 64
Format: MLX safetensors

Sources

1 source

Hugging FacePrimaryVersion fce8edf59f46c91f98fcae6efb588d97069ae737

huggingface.co/mlx-works/Qwopus3.5-4B-Coder-oQ3/tree/fce8edf59f46c91f98fcae6efb588d97069ae737

Verified Oct 21

Model artifacts

1 artifact

model.safetensors

safetensors · 2.50 GB · SHA-256 01c76d6f185a…db25 · Hugging Face

Download

Source excerpts

3 excerpts

ReadmeJul 11huggingface.co/mlx-works/Qwopus3.5-4B-Coder-oQ3

--- library_name: mlx tags: - mlx - oq - quantized --- # Qwopus3.5-4B-Coder-oQ3 This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.4.4) mixed-precision quantization. ## Quantization details - **Model type**: qwen3_5 - **Bits**: 3 - **Group size**: 64 - **Format**: MLX safetensors

NoteOct 21huggingface.co/mlx-works/Qwopus3.5-4B-Coder-oQ3

Source context: 5 downloads · 0 likes · Library mlx · Repo mlx-works/Qwopus3.5-4B-Coder-oQ3

NoteAug 5huggingface.co/mlx-works/Qwopus3.5-4B-Coder-oQ3

Source context: 22 downloads · 0 likes · Library mlx · Repo mlx-works/Qwopus3.5-4B-Coder-oQ3