onde_inference 0.1.1
onde_inference: ^0.1.1 copied to clipboard
On-device LLM inference SDK for Flutter & Dart. Runs Qwen 2.5 models locally with Metal (Apple silicon) and CPU acceleration — no cloud, no data leaving the device. Powered by the Onde Rust engine and [...]
7
likes
-/ -
pub points
345
downloads
This package version is not analyzed. Check the latest stable version for its analysis.
Check the analysis log for details.