Downloads · 30 days
23
12% of all-time downloads
Hunyuan-MT2-1.8B-5bit-MLX
translate-studio/Hunyuan-MT2-1.8B-5bit-MLX
Hunyuan-MT2-1.8B-5bit-MLX is a translation model from translate-studio. Use it when you need text moved from one language to another. It is set up for mlx. The card lists the license as other.
A 5-bit, group-size-64 MLX quantization of Tencent's Hy-MT2-1.8B, for on-device translation on Apple Silicon. ~33 languages, particularly strong into Chinese / Japanese / Korean. Architecture unchanged — this repo onl…
All-time downloads
191
Public
Parameters
1.8B
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 99%
Parameter types
How the weights are stored.
U321.8B · 100%
Base models
Model card
From the Hugging Face model README
Hunyuan-MT2 1.8B — 5-bit (MLX)
A 5-bit, group-size-64 MLX quantization of Tencent's
Hy-MT2-1.8B, for on-device translation on
Apple Silicon. ~33 languages, particularly strong into Chinese / Japanese / Korean. Architecture
unchanged — this repo only re-quantizes the original weights.
| Base model | tencent/Hy-MT2-1.8B |
| Quantization | 5-bit, group size 64, affine |
| Format | MLX safetensors |
| Size | ~1.23 GB |
License & attribution
Subject to the Tencent Hunyuan Community License Agreement — see the license. Use restrictions apply (including commercial-use conditions, and a prohibition on using outputs to train other models). Powered by Tencent Hunyuan. Credit: Tencent. This repository only provides an MLX-quantized copy of the released weights and is redistributed under the same license.
- Task
- Translation
- Library
- mlx
- Type
- hunyuan_v1_dense
- License
- other
- Languages
- multilingual
- Created
- Jul 15, 2026
- Updated
- Jul 15, 2026