Recursive's Flint: Apache 2.0 local coding model hits 125+ tokens/sec on a MacBook Pro
ChengleiSi · x · 2026-10-23
Recursive AI, Richard Socher's startup, released Flint, its first model — a fast local coding model built from scratch in under 4 months by its automated research system, the Eureka Machine. Flint delivers 125+ tokens/sec on a MacBook Pro and 150+ on RTX Spark, claimed up to 2x faster than comparable models, with open weights under Apache 2.0 on Hugging Face. The pitch: private, unmetered intelligence on your own machine, with less dependence on third-party APIs and more control over your own stack.
More from coding & agent
- logplane: A Local Control Plane for AI Agents With Recovery, Approval, Budgets — max_paperclips · 2026-10-23
- SlopCodeBench: Top Model Scores Just 16% on Long-Horizon Coding Agent Benchmark — ajratner · 2026-10-23
- Charter v0.3: a formally verified language for institutional rules with AI constitutional prompts — QuixiAI · 2026-10-23
- DeepSeek harness slashes tokens, time and cost vs Codex, but tanks on FrontierCode — teortaxesTex · 2026-10-23
- The Real Cost of Bad RAG Retrieval Isn't Tokens—It's the Human Cleanup — Street-Ad4993 · 2026-10-23
- Live Sales AI Said "Yes We Support Azure AD"—But It Wasn't in the Notes — SouthWhole7015 · 2026-10-23