Instructions to use appautomaton/trellis2-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use appautomaton/trellis2-mlx-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir trellis2-mlx-8bit appautomaton/trellis2-mlx-8bit
- TRELLIS.2
How to use appautomaton/trellis2-mlx-8bit with TRELLIS.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Licenses for the TRELLIS.2 MLX 8-bit Bundle
This repository combines derivatives of three separately licensed models. No single license replaces the component licenses below.
| Component | Files | Governing terms |
|---|---|---|
| Microsoft TRELLIS.2-4B | ckpts/, pipeline.json, texturing_pipeline.json |
MIT License |
| Meta DINOv3 ViT-L/16 | dinov3/ |
DINOv3 License |
| BRIA RMBG-2.0 | rmbg/ |
CC BY-NC 4.0 attribution and change notice |
The quantization metadata, packaging, and model card describe changes made for
mlx-spatial; they do not relax or replace any upstream term. You must comply
with every license that applies to the files you use or redistribute.
Because the bundle includes RMBG-2.0, use of the complete bundle is limited to non-commercial purposes unless you obtain separate commercial rights from BRIA. The DINOv3 agreement also includes redistribution, trade-control, and other conditions that must be read in full.
This repository is an unofficial derivative and is not affiliated with or endorsed by Microsoft, Meta, BRIA, or the original authors.
Upstream References
- TRELLIS.2-4B: https://huggingface.co/microsoft/TRELLIS.2-4B
- TRELLIS.2 source: https://github.com/microsoft/TRELLIS.2
- DINOv3 ViT-L/16: https://huggingface.co/facebook/dinov3-vitl16-pretrain-lvd1689m
- DINOv3 source: https://github.com/facebookresearch/dinov3
- RMBG-2.0: https://huggingface.co/briaai/RMBG-2.0
- RMBG-2.0 source: https://github.com/Bria-AI/RMBG-2.0