---
title: MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16
canonical_url: "https://www.modelscope.cn/models/mlx-community/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16"
md_url: "https://www.modelscope.cn/models/mlx-community/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16.md"
repository: mlx-community/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16
last_updated: 2026-06-05
license: gemma
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - gemma3
architectures:
  - Gemma3ForConditionalGeneration
base_model:
  - INSAIT-Institute/MamayLM-Gemma-3-27B-IT-v2.0
base_model_relation: finetune
parameters: 27.0B
tensor_type:
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - uk
  - en
downloads: 14
stars: 0
tags:
  - gemma3
  - uk
  - ukrainian
  - mlx
  - mlx-my-repo
---

# MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16

> MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16 - mlx-community 在 ModelScope 开源的模型。mstyslavity/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16

mlx-community/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16 是 ModelScope 魔搭社区上的 27.0B 参数image-text-to-text模型，采用 gemma 许可，基于 INSAIT-Institute/MamayLM-Gemma-3-27B-IT-v2.0 构建。

- **Repository**: mlx-community/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16
- **License**: gemma
- **Tasks**: image-text-to-text
- **Parameters**: 27.0B
- **Base model**: INSAIT-Institute/MamayLM-Gemma-3-27B-IT-v2.0
- **Tags**: gemma3, uk, ukrainian, mlx, mlx-my-repo
- **Downloads**: 14
- **Stars**: 0
- **Last updated**: 2026-06-05

Source: https://www.modelscope.cn/models/mlx-community/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16

---

# mstyslavity/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16

The Model [mstyslavity/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16](https://huggingface.co/mstyslavity/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16) was converted to MLX format from [INSAIT-Institute/MamayLM-Gemma-3-27B-IT-v2.0](https://huggingface.co/INSAIT-Institute/MamayLM-Gemma-3-27B-IT-v2.0) using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mstyslavity/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16")

prompt="hello"

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

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