---
title: firefunction-v2-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/firefunction-v2-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/firefunction-v2-4bit.md"
repository: mlx-community/firefunction-v2-4bit
last_updated: 2025-02-06
license: llama3
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 11.0B
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 884
stars: 0
tags:
  - function-calling
  - mlx
---

# firefunction-v2-4bit

> firefunction-v2-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/firefunction-v2-4bit

mlx-community/firefunction-v2-4bit 是 ModelScope 魔搭社区上的 11.0B 参数机器学习模型，采用 llama3 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/firefunction-v2-4bit
- **License**: llama3
- **Parameters**: 11.0B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: function-calling, mlx
- **Downloads**: 884
- **Stars**: 0
- **Last updated**: 2025-02-06

Source: https://www.modelscope.cn/models/mlx-community/firefunction-v2-4bit

---

# mlx-community/firefunction-v2-4bit

The Model [mlx-community/firefunction-v2-4bit](https://huggingface.co/mlx-community/firefunction-v2-4bit) was converted to MLX format from [fireworks-ai/firefunction-v2](https://huggingface.co/fireworks-ai/firefunction-v2) using mlx-lm version **0.14.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/firefunction-v2-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```