Recursive launches Flint, a local coding model hitting 125+ tokens/sec on MacBook, built in under 4 months
damianplayer · x · 2026-10-22
- Recursive (Richard Socher) launched Flint, a fast local coding model built with its automated research system, the Eureka Machine, from scratch in under 4 months.
- Claims up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark, promising private, unmetered intelligence on-device.
- Open weights are available on Hugging Face; replies are community cheers.
More from Models
- Perplexity's JOLT matches GRPO with 6.5x fewer training tokens, JOLT+ wins on all five benchmarks — perplexity_ai · 2026-10-22
- Recursive AI ships Flint, a 40B-A2.5B MoE claimed to match Qwen3.6-27B, weights on Hugging Face — ChengleiSi · 2026-10-22
- DeepSeek ships V4.1-Flash-1017, now the #1 open model on RSI-Inference Bench — scaling01 · 2026-10-22
- OpenAI's Cybersecurity Guardrails Block a Dev From Auditing His Own Patched Server — Next_Technology6361 · 2026-10-22
- TPN-006 hits Hugging Face: 7.7GB compressed model beats its 17GB Mistral teacher — markjeffrey · 2026-10-22
- Kimi K3.1's latest checkpoint draws 49k-token SVG portrait zero-shot in 22 minutes — lyraxana · 2026-10-22