Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
Python
edge0
Copyright 2026 Edge0
This product is licensed under the Apache License, Version 2.0.
See the LICENSE file.
Third-party notices
-------------------
mlx (third_party/mlx)
Copyright 2023 Apple Inc.
Licensed under the MIT License. See third_party/mlx/LICENSE.
Models
------
Edge0-8B-A1B-preview and Edge0-35B-A3B-preview are published on Hugging Face
under Apache-2.0:
https://huggingface.co/Edge0/Edge0-8B-A1B-preview
https://huggingface.co/Edge0/Edge0-35B-A3B-preview
The upstream inference framework is https://github.com/Edge0-AI/edge0 (Apache-2.0).