Technology

Discover the latest breakthroughs in technology, from innovative startups to major industry shifts. CurioAtlas curates articles on gadgets, software, hardware, and digital culture to keep you ahead of the curve.

Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building…