---
license: apache-2.0
base_model: Qwen/Qwen2.5-1.5B-Instruct
pipeline_tag: text-generation
library_name: mlx
tags:
- mlx
- quantized
- qwen2
---

# Qwen2.5-1.5B-Instruct-MLX-4bit

Plain affine 4-bit (group-size 32) MLX quantization of
[Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
This is the baseline sibling of the DWQ pack — for higher quality at the same
size and bit-width, use the DWQ variant (perplexity 9.45 vs 9.86 here).

## Variants

<!-- sibling-table -->

| Variant | Size | Status |
|---|---|---|
| [Qwen2.5-1.5B-Instruct-MLX-8bit](https://huggingface.co/majentik/Qwen2.5-1.5B-Instruct-MLX-8bit) | 1.5 GB | teacher |
| **Qwen2.5-1.5B-Instruct-MLX-4bit** | **0.93 GB** | **this repo — plain affine 4-bit (gs32)** |
| [Qwen2.5-1.5B-Instruct-MLX-4bit-DWQ](https://huggingface.co/majentik/Qwen2.5-1.5B-Instruct-MLX-4bit-DWQ) | 0.93 GB | DWQ (recommended) |

## Reproduce

```bash
python -m mlx_lm convert --hf-path Qwen/Qwen2.5-1.5B-Instruct \
  --mlx-path Qwen2.5-1.5B-Instruct-MLX-4bit -q --q-bits 4 --q-group-size 32
```

Group-size 32 per `docs/quantization-policy.md` rule 1 (doubles tunable
scale/bias params at low bit width).

## Usage

```bash
pip install mlx-lm
python -m mlx_lm generate --model majentik/Qwen2.5-1.5B-Instruct-MLX-4bit \
  --prompt "The capital of France is"
```

## License

Apache-2.0, inherited from the base model Qwen/Qwen2.5-1.5B-Instruct.