Tencent-Hunyuan · First MLX build 26 May 2026
Hy-MT2-7B
MLX
Text apache-2.0
A 7.5B parameter translation model from Tencent-Hunyuan, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 7.5B From Hugging Face
- Quantisation
- 4-bit Hy-MT2-7B-4bit
- Memory needed
- 7 GB Estimate, unified memory
- Download
- 4.2 GB Weights, estimated
- Downloads
- 790 This build, last 30 days
- Task
- Translation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 7 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Hy-MT2-7B-4bitMLX builds
4 on mlx-community| Hy-MT2-7B-4bit | 4-bit | 4.2 GB | 7 GB | 790 |
|---|---|---|---|---|
| Hy-MT2-7B-8bit | 8-bit | 8.0 GB | 11 GB | 302 |
| Hy-MT2-7B-bf16 | bf16 | 15.0 GB | 19 GB | 66 |
| Hy-MT2-7B | Unstated | 15.0 GB | 19 GB | 56 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.