Recursive SI Releases Flint, a Local Coding Model Hitting 125+ Tokens/s on MacBook
yifengzhu_ut · x · 2026-10-22
Recursive SI released Flint, its first model: a fast local coding model built with its automated research system, the Eureka Machine.
- Claims best-in-class fast local coding, up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro and 150+ on RTX Spark
- Built from scratch in under 4 months
- Pitched as private, unmetered intelligence on your own machine; open weights are on Hugging Face, runnable locally on popular frameworks or free to try on opencode and pidotdev
The reposter, a team member who worked on pretraining and post-training, says Flint is just the start and what matters is the slope.
More from coding & agent
- DuckDB + Hugging Face Amsterdam workshop: build an AI feedback pipeline over 2.1M Amazon reviews — lhoestq · 2026-10-22
- Veracode report: AI now writes half of committed code but only 56% pass security checks — WeldPond · 2026-10-22
- JOLT+ beats GRPO on all five benchmarks, up 9.9 points on AppWorld — perplexity_ai · 2026-10-22
- 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