---
title: codegemma-7b-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/codegemma-7b-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/codegemma-7b-4bit.md"
repository: mlx-community/codegemma-7b-4bit
last_updated: 2025-02-06
license: gemma
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - gemma
architectures:
  - GemmaForCausalLM
parameters: 2.0B
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 859
stars: 0
tags:
  - mlx
---

# codegemma-7b-4bit

> codegemma-7b-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/codegemma-2b-4bit This model was converted to MLX format from google/codegemma-7b using mlx-lm version 0.8.0.

mlx-community/codegemma-7b-4bit 是 ModelScope 魔搭社区上的 2.0B 参数text-generation模型，采用 gemma 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/codegemma-7b-4bit
- **License**: gemma
- **Tasks**: text-generation
- **Parameters**: 2.0B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 859
- **Stars**: 0
- **Last updated**: 2025-02-06

Source: https://www.modelscope.cn/models/mlx-community/codegemma-7b-4bit

---

# mlx-community/codegemma-2b-4bit
This model was converted to MLX format from [`google/codegemma-7b`]() using mlx-lm version **0.8.0**.

Model added by [Prince Canuma](https://twitter.com/Prince_Canuma).

Refer to the [original model card](https://huggingface.co/google/codegemma-7b) 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/codegemma-2b-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```