Instructions to use Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

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

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

pip install mlx mlx-lm

Usage

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

Downloads last month: 19

Safetensors

Model size

4B params

Tensor type

U32

BF16

MLX

Hardware compatibility

8-bit

Model tree for Irfanuruchi/Qwen3-4B-Computer-Science-MLX-8bit

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

Irfanuruchi/Qwen3-4B-Computer-Science

Quantized

(4)

this model