Instructions to use dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX --local-dir Hy-MT2-30B-A3B-oQ8-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download NOTICE from dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX: direct link, hf CLI and curl.
- Browser
- Download file 588 Bytes
-
https://huggingface.co/dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX/resolve/main/NOTICE
- Command line
-
hf download hf://dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX/NOTICE
-
curl -L -o NOTICE https://huggingface.co/dawncr0w/Hy-MT2-30B-A3B-oQ8-MLX/resolve/main/NOTICE
588 Bytes
| Tencent HY is licensed under the Tencent HY Community License Agreement, Copyright © 2026 Tencent. All Rights Reserved. The trademark rights of "Tencent HY" are owned by Tencent or its affiliate. | |
| This repository contains an oQ4 MLX quantized derivative of tencent/Hy-MT2-30B-A3B. | |
| Modified files in this distribution: | |
| - config.json: adds MLX quantization metadata, model_file packaging, and rope_parameters compatibility metadata. | |
| - hy_v3.py: packages the HYV3 MLX model implementation for local model_file loading, with a rope_theta compatibility fallback and absolute mlx_lm imports. | |