---
language:
- en
library_name: mlx
license: mit
license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct-reasoning/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
- nlp
- math
- code
- mlx
- mlx
- mlx-my-repo
widget:
- messages:
  - role: user
    content: How to solve 3*x^2+4*x+5=1?
base_model: lmstudio-community/Phi-4-mini-reasoning-MLX-4bit
---

# introvoyz041/Phi-4-mini-reasoning-MLX-4bit-mlx-4Bit

The Model [introvoyz041/Phi-4-mini-reasoning-MLX-4bit-mlx-4Bit](https://huggingface.co/introvoyz041/Phi-4-mini-reasoning-MLX-4bit-mlx-4Bit) was converted to MLX format from [lmstudio-community/Phi-4-mini-reasoning-MLX-4bit](https://huggingface.co/lmstudio-community/Phi-4-mini-reasoning-MLX-4bit) using mlx-lm version **0.28.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("introvoyz041/Phi-4-mini-reasoning-MLX-4bit-mlx-4Bit")

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)
```