---
title: Phi-3-mini-4k-instruct-4bit-no-q-embed
canonical_url: "https://www.modelscope.cn/models/mlx-community/Phi-3-mini-4k-instruct-4bit-no-q-embed"
md_url: "https://www.modelscope.cn/models/mlx-community/Phi-3-mini-4k-instruct-4bit-no-q-embed.md"
repository: mlx-community/Phi-3-mini-4k-instruct-4bit-no-q-embed
last_updated: 2024-12-19
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - phi3
architectures:
  - Phi3ForCausalLM
parameters: 680.3M
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1000
stars: 0
tags:
  - nlp
  - code
  - mlx
---

# Phi-3-mini-4k-instruct-4bit-no-q-embed

> Phi-3-mini-4k-instruct-4bit-no-q-embed - mlx-community 在 ModelScope 开源的模型。mlx-community/Phi-3-mini-4k-instruct-4bit-no-q-embed This model was converted to MLX format from microsoft/Phi-3-mini-4k-instruct using mlx-lm version 0.12.0. Refer to the original…

mlx-community/Phi-3-mini-4k-instruct-4bit-no-q-embed 是 ModelScope 魔搭社区上的 680.3M 参数text-generation模型，采用 mit 许可，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/Phi-3-mini-4k-instruct-4bit-no-q-embed
- **License**: mit
- **Tasks**: text-generation
- **Parameters**: 680.3M
- **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: nlp, code, mlx
- **Downloads**: 1000
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/Phi-3-mini-4k-instruct-4bit-no-q-embed

---

# mlx-community/Phi-3-mini-4k-instruct-4bit-no-q-embed
This model was converted to MLX format from [`microsoft/Phi-3-mini-4k-instruct`]() using mlx-lm version **0.12.0**.
Refer to the [original model card](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) for more details on the model.
## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Phi-3-mini-4k-instruct-4bit-no-q-embed")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```