Recursive Releases Flint, Its First Open-Weight Coding Model
Recursive has released Flint, its first open-weight coding model, under the Apache 2.0 license. It is a 40B-parameter MoE model aimed at local coding scenarios. Recursive says it reaches over 220 tokens per second on a 64GB RTX Spark, 2x faster than comparable models. Its automated research system, Eureka Machine, also generated custom GPU code that sped up Flint on the RTX Spark by 55% without changing the weights.
Why read this
AI score 68
This piece brings together the model specs, local inference speed, and details of how an automated research system rewrote GPU code, making it easier to judge the usability of a local coding model.
Topics
View original postIntroducing 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, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.
View original
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, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.
Body
Recursive has released Flint, its first open-weight coding model under the Apache 2.0 license, which is 2x faster than comparable alternatives.
> Flint is a 40B parameter mixture-of-experts model for local coding.
> Recursive reports achieving more than 220 tokens per second on a 64GB RTX Spark.
> Recursive's Eureka Machine, a system for running AI research experiments, wrote custom GPU code that sped Flint up by 55% on RTX Spark without changing the weights.