Recursive's Flint Puts a Serious Coding Model on Your Laptop
Recursive released Flint, a 40-billion-parameter coding model built to run on your own machine — and it's quick. With just 2.5 billion parameters active per token, it claims the top spot among sub-50B mixture-of-experts models on agentic coding benchmarks like SWE-Bench Verified, while generating over 125 tokens per second on an M4 Pro MacBook. The weights are on Hugging Face under Apache 2.0 and work with LM Studio, Ollama, and llama.cpp.
Recursive says its optimized inference engine makes Flint roughly twice as fast as comparable models on Apple Silicon and NVIDIA's RTX Spark — and more than five times faster than dense 25–40B models that post similar coding scores.
Source: Recursive — "Introducing Flint", accessed October 24, 2026.
You should also read:
Flint Is Fast, But Qwen 3.8 27B Still Wears the Local Crown
In this article, we examine how the newly released open-weight model Flint compares with the leading local models in the 27B–35B range — and whether Qwen 3.8 27B is still the king, or if Flint has taken the crown. Qwen3.8-27B is a dense 27B-class model…
Continue reading...