The short version
A cross-platform inference engine that can run small machine-learning models in browsers.
From the HackerLinks archive
ONNX Runtime
A cross-platform inference engine that can run small machine-learning models in browsers.
At a glance:
First seen:2026-09-03
Last seen:2026-09-03
Times seen:1
Website:github.com
Why it caught our attention
A commenter reported using it for small in-browser models.
Where it surfaced on Hacker News
2026-09-03
“We use the ONNX runtime for small models in the browser”
seamossfet · recommendation · production use
Direct HN comment
WebLLM: high-performance in-browser LLM inference engine