Socher's Recursive launches Flint, a local coding model hitting 110 tok/s on Mac
_rockt · x · 2026-10-22
Recursive, founded by Richard Socher, released its first model Flint: a fast local coding model claimed to reach 125+ tokens/s on a MacBook Pro and 150+ on RTX Spark, up to 2x faster than comparable models. It was built from scratch in under 4 months by their automated research system, the Eureka Machine, with open weights on Hugging Face.
A user raced Flint against a comparable Qwen model on real coding tasks on a Mac Studio: Flint ran 110 tok/s and nailed every task, while the Qwen model managed only 28 tok/s and thought for 7 minutes on one task without answering. The poster made Flint their new local default.
More from coding & agent
- OpenClaw opens its team environment to community contributors via Focus Weeks — RichardSocher · 2026-10-22
- ESA's cat keyboard incident is a warning for leaving AI agents unattended — vincent_koc · 2026-10-22
- Defense must run at machine speed: agents patch, engineers judge — saranormous · 2026-10-22
- TraceForge synthesizes reasoning traces from answers, beating Claude's own CoT by +3.7/+7.1 — IndependentResearcher121 · 2026-10-22
- Internet Archive fends off PHP attacks overnight, using Claude to patch old code — kingslyj · 2026-10-22
- Combining Ghidra, AI Reverse Engineering and WebGPU Sparks an "Absolute Renaissance" — thursdai_pod · 2026-10-22