---
language:
- en

license: apache-2.0

base_model:
- Irfanuruchi/Qwen3-4B-Computer-Science

pipeline_tag: text-generation

library_name: mlx

tags:
- qwen3
- computer-science
- software-engineering
- programming
- mlx
- mlx-lm
- apple-silicon
- 4-bit
- quantized
- code
- python
- conversational
---

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

## Overview

Qwen3-4B-Computer-Science-MLX-4bit is a 4-bit MLX conversion of
**Qwen3-4B-Computer-Science** for inference on Apple Silicon.

The model was converted from the original BF16 Safetensors release using
`mlx-lm`. It is intended for local inference on supported Mac systems using
the MLX framework.

---

## Model Information

| Property | Value |
|---|---|
| Source model | Irfanuruchi/Qwen3-4B-Computer-Science |
| Base architecture | Qwen3-4B |
| Framework | MLX |
| Quantization | 4-bit |
| Quantization group size | 64 |
| Effective bits per weight | 4.501 |
| Weight format | Safetensors |
| Primary platform | Apple Silicon |
| Language | English |
| License | Apache-2.0 |

---

## Training Data

The source model was instruction-tuned using permissively licensed datasets.

| Dataset | Configuration | License |
|---|---|---|
| HuggingFaceTB/smoltalk | smol-magpie-ultra | Apache-2.0 |
| agentica-org/DeepCoder-Preview-Dataset | primeintellect | MIT |

### Dataset Size

| Split | Samples |
|---|---:|
| Training | 60,989 |
| Evaluation | 512 |

---

## Intended Use

This model is intended for:

- Software engineering
- Programming assistance
- Code generation
- Debugging
- Code review
- Algorithm implementation
- Computer science education
- General technical reasoning

---

## Installation

Install MLX-LM:

```bash
python -m pip install mlx-lm
```

---

## Usage

### Command Line

```bash
mlx_lm.generate \
  --model Irfanuruchi/Qwen3-4B-Computer-Science-MLX-4bit \
  --prompt "Write a Python function that returns the first n Fibonacci numbers." \
  --max-tokens 200
```

### Python

```python
from mlx_lm import generate, load

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

response = generate(
    model,
    tokenizer,
    prompt="Write a Python function that returns the first n Fibonacci numbers.",
    max_tokens=200,
)

print(response)
```

---

## Conversion

The model was converted from:

```text
Irfanuruchi/Qwen3-4B-Computer-Science
```

Conversion configuration:

| Parameter | Value |
|---|---:|
| Quantization enabled | Yes |
| Quantization bits | 4 |
| Quantization group size | 64 |
| Effective bits per weight | 4.501 |

---

## Release Validation

The release was validated locally on Apple Silicon.

| Test | Result |
|---|---|
| MLX conversion | Passed |
| Model loading | Passed |
| Text generation | Passed |
| Generation speed | 53.512 tokens/sec |
| Peak memory | 2.356 GB |

Performance measurements are from one local generation test and may vary by
device, prompt, context length, and software version.

---

## Release Artifacts

```text
model.safetensors
model.safetensors.index.json
config.json
generation_config.json
tokenizer.json
tokenizer_config.json
added_tokens.json
special_tokens_map.json
merges.txt
vocab.json
README.conversion.md
SHA256SUMS
LICENSE
README.md
```

---

## Integrity Verification

Verify the downloaded files on macOS:

```bash
shasum -a 256 -c SHA256SUMS
```

On Linux:

```bash
sha256sum -c SHA256SUMS
```

---

## Limitations

- Quantization can affect output quality relative to the BF16 checkpoint.
- The model may produce incorrect or incomplete code.
- Generated code should be reviewed and tested before use.
- Performance depends on the Apple Silicon device and available memory.
- This release is intended for MLX-compatible systems.

---

## License

The model is distributed under the Apache License 2.0.

The source model is based on Qwen3-4B, which is also distributed under the
Apache License 2.0.

---

## Acknowledgements

- Alibaba Qwen Team
- Apple MLX Team
- Hugging Face
- SmolTalk contributors
- DeepCoder contributors

---

## Citation

```bibtex
@software{uruci2026qwen3computersciencemlx,
  title={Qwen3-4B-Computer-Science-MLX-4bit},
  author={Irfan Uruçi},
  year={2026},
  publisher={Hugging Face}
}
```