Downloads · 30 days
390
73% of all-time downloads
Hy-MT2-1.8B-MLX-4bit
aidsoid/Hy-MT2-1.8B-MLX-4bit
Hy-MT2-1.8B-MLX-4bit is a text generation model from aidsoid. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
A 4-bit quantization of tencent/Hy-MT2-1.8B, Tencent's translation model for 33 languages, converted for Apple silicon with mlx-lm:
All-time downloads
534
Public
Parameters
1.8B
1 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors1 GB · 99%
Parameter types
How the weights are stored.
U321.8B · 100%
Base models
Model card
From the Hugging Face model README
Hy-MT2-1.8B, 4-bit MLX build
A 4-bit quantization of tencent/Hy-MT2-1.8B, Tencent's translation model for 33 languages, converted for Apple silicon with mlx-lm:
mlx_lm convert --hf-path tencent/Hy-MT2-1.8B -q --q-bits 4
Weights are unchanged apart from the quantization (4.5 bits per weight, group size 64). Built for Awnsy, a macOS menu bar translator, where it runs on-device.
Licensed under Apache 2.0, as the original.
- Task
- Text Generation
- Library
- mlx
- Type
- hunyuan_v1_dense
- License
- apache-2.0
- Languages
- zh, en, fr, pt, es, ja
- Created
- Sep 14, 2026
- Updated
- Sep 14, 2026