Tencent · First MLX build 2 Jun 2026
Hy-MT2-7B
MLX
Text apache-2.0
A 7.5B parameter translation model from Tencent, with 2 MLX builds, from 8-bit to bf16.
- Parameters
- 7.5B From Hugging Face
- Quantisation
- bf16 Hy-MT2-7B-Abliterated-bf16
- Memory needed
- 19 GB Estimate, unified memory
- Download
- 15.0 GB Weights, estimated
- Downloads
- 118 This build, last 30 days
- Task
- Translation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 19 GB at bf16
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-Abliterated-bf16MLX builds
2 on mlx-community| Hy-MT2-7B-Abliterated-8bit | 8-bit | 8.0 GB | 11 GB | 113 |
|---|---|---|---|---|
| Hy-MT2-7B-Abliterated-bf16 | bf16 | 15.0 GB | 19 GB | 118 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.