---
title: Phi-4-mini-instruct-mlx-8Bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Phi-4-mini-instruct-mlx-8Bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Phi-4-mini-instruct-mlx-8Bit.md"
repository: mlx-community/Phi-4-mini-instruct-mlx-8Bit
last_updated: 2026-07-27
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - phi3
architectures:
  - Phi3ForCausalLM
base_model:
  - microsoft/Phi-4-mini-instruct
base_model_relation: quantized
parameters: 1.1B
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - multilingual
  - ar
  - zh
  - cs
  - da
  - nl
  - en
  - fi
  - fr
  - de
  - he
  - hu
  - it
  - ja
  - ko
  - no
  - pl
  - pt
  - ru
  - es
  - sv
  - th
  - tr
  - uk
downloads: 21
stars: 0
tags:
  - nlp
  - code
  - mlx
  - mlx-my-repo
---

# Phi-4-mini-instruct-mlx-8Bit

> Phi-4-mini-instruct-mlx-8Bit - mlx-community 在 ModelScope 开源的模型。SkyStar-tech/Phi-4-mini-instruct-mlx-8Bit

mlx-community/Phi-4-mini-instruct-mlx-8Bit 是 ModelScope 魔搭社区上的 1.1B 参数text-generation模型，采用 mit 许可，基于 microsoft/Phi-4-mini-instruct 构建。

- **Repository**: mlx-community/Phi-4-mini-instruct-mlx-8Bit
- **License**: mit
- **Tasks**: text-generation
- **Parameters**: 1.1B
- **Base model**: microsoft/Phi-4-mini-instruct
- **Tags**: nlp, code, mlx, mlx-my-repo
- **Downloads**: 21
- **Stars**: 0
- **Last updated**: 2026-07-27

Source: https://www.modelscope.cn/models/mlx-community/Phi-4-mini-instruct-mlx-8Bit

---

# SkyStar-tech/Phi-4-mini-instruct-mlx-8Bit

The Model [SkyStar-tech/Phi-4-mini-instruct-mlx-8Bit](https://huggingface.co/SkyStar-tech/Phi-4-mini-instruct-mlx-8Bit) was converted to MLX format from [microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) 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("SkyStar-tech/Phi-4-mini-instruct-mlx-8Bit")

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)
```