Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine. Best-in-class fast local coding. Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark. Built from scratch in under 4 months. Private, unmetered intelligence on your own machine. Open weights available now on @huggingface.

Name: Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research sy
Uploaded: 2026-10-21T16:29:32.000Z
Duration: 161 s
Description: Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine. Best-in-class fast local coding. Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark. Built from scratch in under 4 months.

Richard Socher@richardsocher131.1K followers24d ago

Open the original post on X

Views on X

2.9M

Likes

8,320

Reposts

880

Replies

616

Post text

Quoted from X

Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine. Best-in-class fast local coding. Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark. Built from scratch in under 4 months. Private, unmetered intelligence on your own machine. Open weights available now on @huggingface.

This entry is part of the launch video directory and the AI Coding launch videos. Counts are read from X every 15 minutes; see the methodology.