---
title: gemma-4-12B-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/gemma-4-12B-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/gemma-4-12B-4bit.md"
repository: mlx-community/gemma-4-12B-4bit
last_updated: 2026-06-05
license: apache-2.0
pipeline_tag: any-to-any
tasks:
  - any-to-any
model_type:
  - gemma4_unified
architectures:
  - Gemma4UnifiedForConditionalGeneration
base_model:
  - google/gemma-4-12B
base_model_relation: quantized
parameters: 2.9B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 66
stars: 0
tags:
  - mlx
---

# gemma-4-12B-4bit

> gemma-4-12B-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/gemma-4-12B-4bit

mlx-community/gemma-4-12B-4bit 是 ModelScope 魔搭社区上的 2.9B 参数any-to-any模型，采用 apache-2.0 许可，基于 google/gemma-4-12B 构建。

- **Repository**: mlx-community/gemma-4-12B-4bit
- **License**: apache-2.0
- **Tasks**: any-to-any
- **Parameters**: 2.9B
- **Base model**: google/gemma-4-12B
- **Tags**: mlx
- **Downloads**: 66
- **Stars**: 0
- **Last updated**: 2026-06-05

Source: https://www.modelscope.cn/models/mlx-community/gemma-4-12B-4bit

---

# mlx-community/gemma-4-12B-4bit

This model was converted to MLX format from [`google/gemma-4-12B`](https://huggingface.co/google/gemma-4-12B)
using mlx-vlm version **0.6.0**.
Refer to the [original model card](https://huggingface.co/google/gemma-4-12B) for more details on the model.

## Use with mlx

```bash
pip install -U mlx-vlm
```

```bash
python -m mlx_vlm.generate --model mlx-community/gemma-4-12B-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```