---
license: apache-2.0
base_model: empero-ai/Qwen3.8-2B-Distill
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- empero-ai
- qwen3.5
- qwen3.8
- distillation
- reasoning
- function-calling
- sft
- edge
- mlx
- mlx-my-repo
---

# keXjos/Qwen3.8-2B-Distill-mlx-5Bit

The Model [keXjos/Qwen3.8-2B-Distill-mlx-5Bit](https://huggingface.co/keXjos/Qwen3.8-2B-Distill-mlx-5Bit) was converted to MLX format from [empero-ai/Qwen3.8-2B-Distill](https://huggingface.co/empero-ai/Qwen3.8-2B-Distill) using mlx-lm version **0.31.2**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("keXjos/Qwen3.8-2B-Distill-mlx-5Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```