https://github.com/ondeinference/onde
https://github.com/ondeinference/onde
inference-engine on-device-ai on-device-inference
Last synced: 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/ondeinference/onde
- Owner: ondeinference
- License: apache-2.0
- Created: 2026-03-04T15:28:38.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2026-04-08T21:30:38.000Z (3 months ago)
- Last Synced: 2026-04-08T22:27:28.558Z (3 months ago)
- Topics: inference-engine, on-device-ai, on-device-inference
- Language: Rust
- Homepage: https://ondeinference.com
- Size: 468 KB
- Stars: 15
- Watchers: 0
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE-APACHE
- Agents: AGENTS.md
Awesome Lists containing this project
README
Onde Inference
On-device LLM inference — optimized for Apple silicon.
Swift SDK · Flutter SDK · React Native SDK · Website
---
## In production
Onde powers live App Store apps with fully on-device chat — no server, no latency, no data leaving the device.
---
## License
Onde is dual-licensed under **MIT** and **Apache 2.0**. You may use it under either license at your option.
- [MIT License](LICENSE-MIT)
- [Apache License 2.0](LICENSE-APACHE)
### Dependency attribution
| Dependency | License | Author |
|---|---|---|
| [mistral.rs](https://github.com/EricLBuehler/mistral.rs) | MIT | Eric Buehler |
| [UniFFI](https://github.com/mozilla/uniffi-rs) | MPL-2.0 | Mozilla |
| [tokio](https://github.com/tokio-rs/tokio) | MIT | Tokio contributors |
### Model licenses
Models downloaded by Onde have their own licenses independent of this crate. By using Onde, you are also subject to the license of the model you load:
| Model | License |
|---|---|
| Qwen 2.5 1.5B / 3B Instruct | [Qwen Community License](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct/blob/main/LICENSE) |
| Qwen 2.5 Coder 1.5B / 3B / 7B | [Qwen Community License](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct/blob/main/LICENSE) |
---
© 2026 Onde Inference