---
title: Llama-3.2-3B-Instruct-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Llama-3.2-3B-Instruct-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/Llama-3.2-3B-Instruct-bf16.md"
repository: mlx-community/Llama-3.2-3B-Instruct-bf16
last_updated: 2024-12-20
license: llama3.2
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 3.2B
tensor_type:
  - BF16
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: 989
stars: 0
tags:
  - facebook
  - meta
  - pytorch
  - llama
  - llama-3
  - mlx
---

# Llama-3.2-3B-Instruct-bf16

> Llama-3.2-3B-Instruct-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/Llama-3.2-3B-Instruct-bf16

mlx-community/Llama-3.2-3B-Instruct-bf16 是 ModelScope 魔搭社区上的 3.2B 参数text-generation模型，采用 llama3.2 许可，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-bf16
- **License**: llama3.2
- **Tasks**: text-generation
- **Parameters**: 3.2B
- **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**: 989
- **Stars**: 0
- **Last updated**: 2024-12-20

Source: https://www.modelscope.cn/models/mlx-community/Llama-3.2-3B-Instruct-bf16

---

# mlx-community/Llama-3.2-3B-Instruct-bf16

The Model [mlx-community/Llama-3.2-3B-Instruct-bf16](https://huggingface.co/mlx-community/Llama-3.2-3B-Instruct-bf16) 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 **0.17.1**.

## 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-bf16")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```