Recursive SI launches Flint: open-weights local coding model at 125+ tokens/sec on MacBook Pro
JafarNajafov · x · 2026-10-22
Recursive SI introduced Flint, its first model: a fast local coding model built from scratch in under 4 months by its automated research system, the Eureka Machine. It claims 125+ tokens/sec on a MacBook Pro and 150+ on RTX Spark — up to 2x faster than comparable models. Open weights are on Hugging Face, pitching private, unmetered local intelligence.
More from coding & agent
- Hamel Husain and Shreya Shankar Launch 'Evals for AI Engineers' Book Nov 12 — HamelHusain · 2026-10-22
- EAU meta-agent automates RL training: 36.7% higher task completion on ColBench — xiye_nlp · 2026-10-22
- EAU's three designs: hybrid user sim, evolving rewards, hot-swapped components — xiye_nlp · 2026-10-22
- EAU Meta-Agent Automates Agentic RL Training, Beating Expert-Designed Pipelines — xiye_nlp · 2026-10-22
- Mastercard teams with Coinbase on x402 agentic payments for AI agents — MurrLincoln · 2026-10-22
- One prompt to replicate papers: 7/10 found data problems, 3/10 simpler baselines won — generativist · 2026-10-22