Downloads · 30 days
42
5% of all-time downloads
Hy-MT2-30B-A3B-oQ4-MLX
dawncr0w/Hy-MT2-30B-A3B-oQ4-MLX
Hy-MT2-30B-A3B-oQ4-MLX is a translation model from dawncr0w. 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.
This is an oQ4 MLX quantized derivative of tencent/Hy-MT2-30B-A3B.
All-time downloads
824
Public
Parameters
30.1B
17.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.4 GB · 100%
Parameter types
How the weights are stored.
U3230.1B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Hy-MT2-30B-A3B-oQ4-MLX
This is an oQ4 MLX quantized derivative of tencent/Hy-MT2-30B-A3B.
The model was quantized locally with oMLX oQ4. The resulting config targets approximately 4.62 bpw and includes a packaged hy_v3.py model file so MLX-LM can load the HYV3 architecture from the model directory.
Validation
Local validation completed with the oMLX app bundle on macOS:
mlx_lm load: passed
generation smoke test: passed
prompt: Hello
max tokens: 4
peak memory: 17.435 GB
Usage
Use an MLX-LM build that supports the APIs used by the packaged hy_v3.py file.
python -m mlx_lm generate \
--model /path/to/Hy-MT2-30B-A3B-oQ4-MLX \
--ignore-chat-template \
--prompt "Hello" \
--max-tokens 32 \
--temp 0
License And Notice
The base model is distributed under the Tencent HY Community License Agreement. This distribution includes LICENSE.txt and NOTICE from/for the Tencent HY license requirements.
This repository is not affiliated with, sponsored by, or endorsed by Tencent.
- Task
- Translation
- Library
- mlx
- Type
- hy_v3
- License
- other
- Languages
- zh, en, fr, pt, es, ja
- Created
- May 26, 2026
- Updated
- May 26, 2026