Team Ai
Modelpublic

Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face
0likes17downloads
Model Card

Qwen3-4B-Computer-Science-MLX-8bit

An Apple MLX 8-bit quantized version of Qwen3-4B-Computer-Science, optimized for efficient local inference on Apple Silicon Macs.

This repository provides an MLX-compatible model for fast inference while maintaining excellent quality with significantly reduced memory usage.

Base Model

  • —Base repository: Irfanuruchi/Qwen3-4B-Computer-Science
  • —Architecture: Qwen3-4B
  • —Format: MLX
  • —Quantization: 8-bit
  • —Group Size: 64

Features

  • —Optimized for Apple Silicon (M-series)
  • —Fast local inference using MLX
  • —Reduced memory footprint
  • —Compatible with mlx-lm

Installation

bash
python3 -m venv .venv
source .venv/bin/activate

pip install mlx mlx-lm

Usage

bash
mlx_lm.generate \
  --model Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit \
  --prompt "Write a Python function that validates an IPv4 address." \
  --max-tokens 256

License

This model is released under the Apache 2.0 License.

The original Qwen3 model is licensed under Apache 2.0. This repository contains an MLX quantized version of the original weights.

Acknowledgements

  • —Alibaba Qwen Team
  • —Apple MLX
  • —Hugging Face