---
title: medgemma-27b-text-it-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/medgemma-27b-text-it-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/medgemma-27b-text-it-4bit.md"
repository: mlx-community/medgemma-27b-text-it-4bit
last_updated: 2025-06-09
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - gemma3_text
architectures:
  - Gemma3ForCausalLM
parameters: 4.4B
tensor_type:
  - U32
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 356
stars: 0
---

# medgemma-27b-text-it-4bit

> medgemma-27b-text-it-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/medgemma-27b-text-it-4bit

mlx-community/medgemma-27b-text-it-4bit 是 ModelScope 魔搭社区上的 4.4B 参数image-text-to-text模型，可用 deploy_task text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/medgemma-27b-text-it-4bit
- **Tasks**: image-text-to-text
- **Parameters**: 4.4B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 356
- **Stars**: 0
- **Last updated**: 2025-06-09

Source: https://www.modelscope.cn/models/mlx-community/medgemma-27b-text-it-4bit

---

# mlx-community/medgemma-27b-text-it-4bit

This model [mlx-community/medgemma-27b-text-it-4bit](https://huggingface.co/mlx-community/medgemma-27b-text-it-4bit) was
converted to MLX format from [google/medgemma-27b-text-it](https://huggingface.co/google/medgemma-27b-text-it)
using mlx-lm version **0.25.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/medgemma-27b-text-it-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```