NaiveAI Open-Sources 309B MoE Model Built Largely by AI Itself

NaiveAI open-sourced Naive-N0.5-Flash, a 309B-parameter MoE model with 15.5B active parameters, 1M-token context and 2000 tok/s inference, developed largely by AI with humans setting goals and constraints.

2026-09-28 ~ 2026-09-28 · 3 related posts

• NaiveAI open-sources Naive-N0.5-Flash: a 309B MoE built by AI itself, up to 2,000 tok/s inference — Xianbao_QIAN · 2026-09-28
• Naive Releases 309B-A15.5B MoE Model Naive-N0.5-Flash With 1M Context for Coding — nullmove · 2026-09-28
• NaiveAI's first model is built and trained largely by AI itself, cutting decode latency 72% — 机器之心 · 2026-09-28