StudioRecursive AI Releases Flint, Its First Open-Weight Local Coding Model
Original title: Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated r…
Recursive AI has launched Flint, its first model, a fast local coding tool built by its automated research system, Eureka Machine. It achieves over 125 tokens per second on a MacBook Pro and over 150 tokens per second on an RTX Spark, claiming to be up to twice as fast as comparable models. Developed in under four months, the open-weight model is available on Hugging Face for free trial via opencode or pidotdev.
The original text provides specific speed metrics and device performance data, allowing readers to assess the practicality of this local coding model.
The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.