Recursive launches Flint: local coding model built in 4 months, 125+ tok/s on MacBook
ChengleiSi · x · 2026-10-22
Richard Socher announces Flint, Recursive AI's first model: a fast local coding model built from scratch in under 4 months by their automated research system, the Eureka Machine.
- Speed: up to 2x faster than comparable models — 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark
- Benchmarks: per official charts, Flint 40B (2B active) scores 54.9 on Terminal-Bench 2.1, 89.7 on SWE-bench Pro v2, 74.2 on SWE-bench Verified, 80.3 on LiveCodeBench v6 and 95.1 on IFEval, leading comparable local MoE and 27–31B dense models on several
- Open: weights available on Hugging Face, runnable locally or free via opencode / pidotdev, pitching private, unmetered local intelligence
More from coding & agent
- Will Brown: Continual Learning in the Harness Is Like a Computer Without RAM — willcb · 2026-10-22
- Migrating an entire Hermes automation workload to Antigravity took about 2 hours — rseroter · 2026-10-22
- How a second Mac mini lets AI agents auto-distribute compute-heavy tasks — tedddyoweh · 2026-10-22
- LangChain's Design Agent Shipped 3,000+ Assets and Earned 4.5M Views Since August — LangChain · 2026-10-22
- Handling MCP Tool Calls That Take Minutes: Client Timeout Practices Explored — Hot_Bee_5451 · 2026-10-22
- After 18 Months Selling AI Agents, Here's What Nobody Tells You — NailComprehensive314 · 2026-10-22