---
title: Llama-3.2-3B-Instruct
canonical_url: "https://www.modelscope.cn/models/mlx-community/Llama-3.2-3B-Instruct"
md_url: "https://www.modelscope.cn/models/mlx-community/Llama-3.2-3B-Instruct.md"
repository: mlx-community/Llama-3.2-3B-Instruct
last_updated: 2025-02-06
license: llama3.2
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - meta-llama/Llama-3.2-3B-Instruct
base_model_relation: finetune
parameters: 3.2B
tensor_type:
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - de
  - fr
  - it
  - pt
  - hi
  - es
  - th
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 868
stars: 0
tags:
  - facebook
  - meta
  - pytorch
  - llama
  - llama-3
  - mlx
---

# Llama-3.2-3B-Instruct

> Llama-3.2-3B-Instruct - mlx-community 在 ModelScope 开源的模型。mlx-community/Llama-3.2-3B-Instruct

mlx-community/Llama-3.2-3B-Instruct 是 ModelScope 魔搭社区上的 3.2B 参数text-generation模型，采用 llama3.2 许可，基于 meta-llama/Llama-3.2-3B-Instruct 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/Llama-3.2-3B-Instruct
- **License**: llama3.2
- **Tasks**: text-generation
- **Parameters**: 3.2B
- **Base model**: meta-llama/Llama-3.2-3B-Instruct
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: facebook, meta, pytorch, llama, llama-3, mlx
- **Downloads**: 868
- **Stars**: 0
- **Last updated**: 2025-02-06

Source: https://www.modelscope.cn/models/mlx-community/Llama-3.2-3B-Instruct

---

# mlx-community/Llama-3.2-3B-Instruct

The Model [mlx-community/Llama-3.2-3B-Instruct](https://huggingface.co/mlx-community/Llama-3.2-3B-Instruct) was converted to MLX format from [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) using mlx-lm version **0.18.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Llama-3.2-3B-Instruct")

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)
```