Recursive releases 40B hybrid expert coding model Flint
The story so far
No overview yet — start with the coverage timeline below.
Developments
3 developments
- 22 Oct, 05:46 · 1 reportsVersion v0.40.8 is releasedOllama releases:v0.40.8
- 22 Oct, 04:27 · 2 reportsRecursive launches Flint, a laptop coding model it says wasThe Decoder:Recursive shows first result of its AI-driven research process with Flint
- 21 Oct, 08:00 · 2 reportsRecursive Flint on OpenHands: Open Models, Real Coding WorkfvLLM Blog:Day-0 Support for Flint on vLLM
Coverage timeline
Follow the coverage to see every side of the story.
- The DecoderFeaturedRecursive shows first result of its AI-driven research process with Flint
AI startup Recursive has released its first language model, Flint. During the development process, the AI system named Eureka Machine participated in proposing ideas, building, testing, and planning subsequent experiments.
- Ollama releasesv0.40.8
Recursive Flint v0.40.8 released, bringing code intelligence agents to Ollama. The 40B parameter MoE model supports 262K token context and achieves 54.9% on Terminal-Bench 2.1 and 74.2% on SWE-bench Verified. Flint can be used for code understanding, debugging, feature implementation, and testing, and supports MacOS.
- TechCrunch · AIRecursive launches Flint, a laptop coding model it says was largely built by AI
Recursive releases its first model, Flint, a free coding model that can run on laptops, with almost the entire development process driven by AI. Recursive's automated research system, Eureka Machine, participated in almost every development step of Flint, enabling the team to complete the model construction in less than four months.
- vLLM BlogFeaturedDay-0 Support for Flint on vLLM
vLLM announced support on the day Flint was released, with both NVFP4 and BF16 checkpoints capable of running on a single GPU, decoding approximately 500 tokens/s per request on a single GB200 with a context of 100,000 tokens.
- OpenHands BlogRecursive Flint on OpenHands: Open Models, Real Coding Workflows
Recursive Flint is released, a hybrid expert model with 4 billion parameters, designed for efficient local inference, activating only about 250 million parameters per token, achieving 125+ tokens/second on M4 Pro MacBook Pro, and reaching 150+ tokens/second on NVIDIA RTX Spark. OpenHands, as its first partner, supports the model's operation on local hardware, providing developers with an open-source coding model option.