Recursive launches Flint: a 40B MoE local coding model activating just 2.5B params

cong_ml · x · 2026-10-22

Recursive introduced Flint, a mixture-of-experts model for fast agentic coding on local hardware: 40B total parameters with only 2.5B active per token.

• Leads MoE models under 50B on agentic coding benchmarks (SWE-Bench Pro v2, Terminal-Bench 2.1, SWE-Bench Verified)
• 125+ tok/s on an M4 Pro MacBook and 150+ tok/s on a 64GB RTX Spark at short context; up to 256k context recommended
• Built in under four months with nearly every part of the stack developed by Recursive's automated research system, the Eureka Machine

Related event: Recursive releases Flint, an open-weights 40B MoE coding model built in under 4 months by its automated Eureka research system(50 posts)→

Original post →

More from Infra

• SPCX earnings call highlights 'computer per watt' metric as AI value shifts down the stack — mobileraj · 2026-10-22
• Eureka Machine runs on Mac inference so quietly the author's MacBook barely spins its fans — cong_ml · 2026-10-22
• Compute demand is so hot it's becoming a month-to-month auction, analysts say long-term contracts are dying — BenBajarin · 2026-10-22
• SGLang ran early RL training on TPUs with Miles and TorchTitan, with promising results — ying11231 · 2026-10-22
• CXMT's market cap tops all mid-size Asian fabs combined, half of SK Hynix — pstAsiatech · 2026-10-22
• SemiAnalysis: DeepSeek's open-sourced DeepInfer lacks key inference-serving components — cHHillee · 2026-10-22

Infra channel →