---
title: HY-MT1.5-7B-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/HY-MT1.5-7B-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/HY-MT1.5-7B-8bit.md"
repository: mlx-community/HY-MT1.5-7B-8bit
last_updated: 2026-01-04
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - hunyuan_v1_dense
architectures:
  - HunYuanDenseV1ForCausalLM
base_model:
  - tencent/HY-MT1.5-7B
base_model_relation: quantized
parameters: 2.1B
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - zh
  - en
  - fr
  - pt
  - es
  - ja
  - tr
  - ru
  - ar
  - ko
  - th
  - it
  - de
  - vi
  - ms
  - id
  - tl
  - hi
  - pl
  - cs
  - nl
  - km
  - my
  - fa
  - gu
  - ur
  - te
  - mr
  - he
  - bn
  - ta
  - uk
  - bo
  - kk
  - mn
  - ug
inference_backends:
  - "deploy_task text"
  - "sglang 0.5.2"
downloads: 38
stars: 0
tags:
  - transformers
  - mlx
  - translation
---

# HY-MT1.5-7B-8bit

> HY-MT1.5-7B-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/HY-MT1.5-7B-8bit

mlx-community/HY-MT1.5-7B-8bit 是 ModelScope 魔搭社区上的 2.1B 参数text-generation模型，基于 tencent/HY-MT1.5-7B 构建，可用 deploy_task text、sglang 0.5.2 部署。

- **Repository**: mlx-community/HY-MT1.5-7B-8bit
- **Tasks**: text-generation
- **Parameters**: 2.1B
- **Base model**: tencent/HY-MT1.5-7B
- **Inference backends**: deploy_task text, sglang 0.5.2
- **Tags**: transformers, mlx, translation
- **Downloads**: 38
- **Stars**: 0
- **Last updated**: 2026-01-04

Source: https://www.modelscope.cn/models/mlx-community/HY-MT1.5-7B-8bit

---

# mlx-community/HY-MT1.5-7B-8bit

The Model [mlx-community/HY-MT1.5-7B-8bit](https://huggingface.co/mlx-community/HY-MT1.5-7B-8bit) was converted to MLX format from [tencent/HY-MT1.5-7B](https://huggingface.co/tencent/HY-MT1.5-7B) using mlx-lm version **0.29.1**.

You can find other similar translation-related MLX model quants for an Apple Mac at https://huggingface.co/bibproj

The following parameters values are recommended for inference:
* top_k: 20
* top_p: 0.6
* repetition_penalty: 1.05
* temperature: 0.7

36 Supported Languages: Chinese, English, French, Portuguese, Spanish, Japanese, Turkish, Russian, Korean, Thai, Italian, German, Vietnamese, Malay, Indonesian, Filipino, Hindi, Traditional Chinese, Polish, Czech, Dutch, Khmer, Burmese, Persian, Gujarati, Urdu, Telugu, Marathi, Hebrew, Bengali, Tamil, Ukrainian, Tibetan, Kazakh, Mongolian, Uyghur, and Cantonese.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/HY-MT1.5-7B-8bit")

prompt="Translate from English to French: Hi there!"

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)
```