---
title: Hy-MT2-7B
canonical_url: "https://www.modelscope.cn/models/mlx-community/Hy-MT2-7B"
md_url: "https://www.modelscope.cn/models/mlx-community/Hy-MT2-7B.md"
repository: mlx-community/Hy-MT2-7B
last_updated: 2026-06-01
license: apache-2.0
pipeline_tag: translation
tasks:
  - translation
model_type:
  - hunyuan_v1_dense
architectures:
  - HunYuanDenseV1ForCausalLM
base_model:
  - Tencent-Hunyuan/Hy-MT2-7B
base_model_relation: finetune
parameters: 7.5B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - multilingual
downloads: 43
stars: 0
tags:
  - mlx
  - apple-silicon
  - mlx-lm
  - translation
  - hunyuan_v1_dense
---

# Hy-MT2-7B

> Hy-MT2-7B - mlx-community 在 ModelScope 开源的模型。Part of the Hy-MT2 MLX collection.

mlx-community/Hy-MT2-7B 是 ModelScope 魔搭社区上的 7.5B 参数translation模型，采用 apache-2.0 许可，基于 Tencent-Hunyuan/Hy-MT2-7B 构建。

- **Repository**: mlx-community/Hy-MT2-7B
- **License**: apache-2.0
- **Tasks**: translation
- **Parameters**: 7.5B
- **Base model**: Tencent-Hunyuan/Hy-MT2-7B
- **Tags**: mlx, apple-silicon, mlx-lm, translation, hunyuan_v1_dense
- **Downloads**: 43
- **Stars**: 0
- **Last updated**: 2026-06-01

Source: https://www.modelscope.cn/models/mlx-community/Hy-MT2-7B

---

Part of the [Hy-MT2 MLX](https://huggingface.co/collections/mlx-community/hy-mt2-6a15a173a4e2d27031541558) collection.

# Hy-MT2-7B (MLX)

Apple MLX weights for [Tencent-Hunyuan/Hy-MT2-7B](https://github.com/Tencent-Hunyuan/Hy-MT2), Tencent Hunyuan's multilingual translation model.

This default repository is the bf16 variant and is equivalent to [`mlx-community/Hy-MT2-7B-bf16`](https://huggingface.co/mlx-community/Hy-MT2-7B-bf16). Use this repo when you want the recommended default checkpoint.

## TL;DR

| | |
|---|---|
| **Variant** | 7B default bf16 (`bfloat16`) |
| **Best for** | converted high-precision 7B checkpoint; requires more memory |
| **Runtime** | [`mlx-lm`](https://github.com/ml-explore/mlx-lm) |
| **Official code** | [`Tencent-Hunyuan/Hy-MT2`](https://github.com/Tencent-Hunyuan/Hy-MT2) |
| **MLX code** | [`ailuntx/Hy-MT2-MLX`](https://github.com/ailuntx/Hy-MT2-MLX) |
| **Hardware** | Apple Silicon recommended; HF Spaces CPU fallback is only a load smoke test |

## Quick Start

```bash
pip install mlx-lm
PROMPT=$'Translate the following text into English. Note that you should only output the translated result without any additional explanation:\n\n今天天气真好。'
mlx_lm.generate --model mlx-community/Hy-MT2-7B \
  --prompt "$PROMPT" \
  --max-tokens 128 \
  --temp 0.7 \
  --top-p 0.6 \
  --top-k 20
```

For conversion and staging tools:

```bash
git clone https://github.com/ailuntx/Hy-MT2-MLX.git
cd Hy-MT2-MLX
python scripts/infer_mlx.py --model /path/to/mlx/checkpoint --text "今天天气真好。" --target-lang English
```

## Variants

| Variant | Best for |
|---|---|
| [`Hy-MT2-1.8B`](https://huggingface.co/mlx-community/Hy-MT2-1.8B) | default 1.8B checkpoint, same weights as bf16 |
| [`Hy-MT2-1.8B-bf16`](https://huggingface.co/mlx-community/Hy-MT2-1.8B-bf16) | high-quality 1.8B bf16 baseline |
| [`Hy-MT2-1.8B-8bit`](https://huggingface.co/mlx-community/Hy-MT2-1.8B-8bit) | smaller 1.8B checkpoint |
| [`Hy-MT2-1.8B-4bit`](https://huggingface.co/mlx-community/Hy-MT2-1.8B-4bit) | smallest 1.8B checkpoint |
| [`Hy-MT2-7B`](https://huggingface.co/mlx-community/Hy-MT2-7B) | default 7B checkpoint, same weights as bf16 |
| [`Hy-MT2-7B-bf16`](https://huggingface.co/mlx-community/Hy-MT2-7B-bf16) | explicit high-precision 7B bf16 conversion |
| [`Hy-MT2-7B-8bit`](https://huggingface.co/mlx-community/Hy-MT2-7B-8bit) | 7B size/quality middle ground |
| [`Hy-MT2-7B-4bit`](https://huggingface.co/mlx-community/Hy-MT2-7B-4bit) | smallest 7B checkpoint |

## Conversion Notes

| Component | Source | MLX handling |
|---|---|---|
| model weights | official dense Hy-MT2 checkpoint | converted with MLX/`mlx-lm` tooling |
| tokenizer/config | official checkpoint | copied through for `mlx-lm` loading |
| quantized variants | bf16 (`bfloat16`) MLX baseline | derived with MLX quantization settings |

## Validation

Local Apple Silicon is the intended runtime. The Hy-MT2 HF Space starts and loads the model on Linux CPU fallback, but `cpu-basic` can exceed request timeouts even for very small generation tests.

## License

License follows the upstream Tencent Hunyuan release.

## Citation

```bibtex
@misc{hymt2-mlx,
  title  = {Hy-MT2-MLX: Apple MLX port of Hy-MT2},
  author = {ailuntx},
  year   = {2026},
  url    = {https://github.com/ailuntx/Hy-MT2-MLX},
}

@misc{zheng2026hymt2familyfastefficient,
  title         = {Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild},
  author        = {Mao Zheng and Zheng Li and Tao Chen and Bo Lv and Mingrui Sun and Mingyang Song and Jinlong Song and Hong Huang and Decheng Wu and Hai Wang and Yifan Song and Yanfeng Chen and Guanwei Zhang},
  year          = {2026},
  eprint        = {2605.22064},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2605.22064},
}
```