Instructions to use zero0303/maya2-mlx-dynamic-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use zero0303/maya2-mlx-dynamic-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download zero0303/maya2-mlx-dynamic-8bit --local-dir maya2-mlx-dynamic-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
|
Download NOTICE.md from zero0303/maya2-mlx-dynamic-8bit: direct link, hf CLI and curl.
- Browser
- Download file 2.23 kB
-
https://huggingface.co/zero0303/maya2-mlx-dynamic-8bit/resolve/main/NOTICE.md
- Command line
-
hf download hf://zero0303/maya2-mlx-dynamic-8bit/NOTICE.md
-
curl -L -o NOTICE.md https://huggingface.co/zero0303/maya2-mlx-dynamic-8bit/resolve/main/NOTICE.md
2.23 kB
| # Notices and attribution | |
| This repository is an independent MLX (Apple Silicon) port of **Maya 2 Native** by Maya Research. It is not an | |
| official Maya Research release. | |
| ## Maya 2 Native (model weights and code), Apache-2.0 | |
| - Model: [maya-research/maya2-native](https://huggingface.co/maya-research/maya2-native), © Maya Research, | |
| Apache-2.0 (`LICENSE`, copied unchanged from the release). | |
| - Code: [MayaResearch/maya2-native](https://github.com/MayaResearch/maya2-native), commit `c6b3768`, Apache-2.0. | |
| - Changes in this repository: | |
| - The weights were re-laid out for MLX. | |
| - `models/maya2-8bit` quantizes most backbone tensors, the token embeddings and the feedback table to 8 bits (the | |
| recipe is in its `quant.json`). | |
| - The inference code was rewritten for MLX in `maya2_mlx/`. | |
| - `maya3/guards.py`, `maya3/assets/`, `maya3/text/`, `maya3/__init__.py` and `configs/text_frames_prior.json` are | |
| copied unchanged from the official repository. | |
| - Built-in voice names identify synthetic personas, not real people. Follow the original model card's intended-use | |
| and responsible-deployment section: disclose synthetic speech, no impersonation or deception. | |
| ## Kyutai Mimi (audio codec weights), CC-BY-4.0 | |
| - Model: [kyutai/mimi](https://huggingface.co/kyutai/mimi), © Kyutai, licensed under | |
| [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/). | |
| - `models/*/mimi.safetensors` holds Mimi's decoder: the quantizer codebooks, the upsampler, the decoder transformer | |
| and the SEANet decoder. | |
| - Changes: convolution weights re-laid out for MLX, codebook embeddings stored as computed (embed_sum / cluster | |
| usage), RoPE tables precomputed, encoder weights left out. Values are otherwise unchanged (fp32). | |
| ## Qwen3 (backbone architecture), Apache-2.0 | |
| The backbone has the Qwen3-1.7B architecture (Qwen team, Alibaba, Apache-2.0). Its weights here are Maya 2 Native's | |
| trained weights, not Qwen's. | |
| ## Citation of the original model | |
| ```bibtex | |
| @misc{maya2native2026, | |
| title = {Maya 2 Native: Streaming Multilingual Text-to-Speech}, | |
| author = {{Maya Research}}, | |
| year = {2026}, | |
| url = {https://huggingface.co/maya-research/maya2-native}, | |
| note = {Release 1.0} | |
| } | |
| ``` | |