NaiveAI open-sources Naive-N0.5-Flash: a 309B MoE built by AI itself, up to 2,000 tok/s inference
Xianbao_QIAN · x · 2026-09-28
NaiveAI has released and open-sourced (MIT license) Naive-N0.5-Flash, pitched as "building frontier AI with AI":
- Architecture: 309B MoE with 15.5B active parameters; native 1M context with no full-attention layers, combining SWA with lightweight DeepSeek Sparse Attention (DSA).
- Focus: coding and AI R&D; the model is trained to participate in the R&D process itself, opening a path toward recursive self-improvement (RSI).
- AI-driven R&D: AI explored the hybrid attention design and optimized training, inference, and deployment, while humans set direction and made key decisions. The supporting infrastructure serves 10 million sandboxes weekly with 100,000 concurrent at peak.
- Inference: AI-optimized runtime reaching up to 2,000 tokens/s in Ultrafast mode.
Weights are live on Hugging Face and GitHub, with an accompanying tech blog.
Related event: NaiveAI Open-Sources 309B MoE Model N0.5-Flash(2 posts)→
More from Models
- Community Speculates OpenAI's New Agent Name: Reviving "Orion" Over "o." — brandon_galang · 2026-09-28
- Princeton professor points out Ember and GLM aren't on the cost-performance Pareto frontier — random_walker · 2026-09-28
- Users Report Claude Forcing Re-Login Every 2-3 Days, Calling It Exhausting — weswinder · 2026-09-28
- Naive Releases 309B-A15.5B MoE Model Naive-N0.5-Flash With 1M Context for Coding — nullmove · 2026-09-28
- Tokens Are Perfect for Shrinkflation — and Anthropic's Opus Pricing Shift Pressures OpenAI — StewartalsopIII · 2026-09-28
- Benchmark Heaven hits 130k visits in 10 days with cost-capability model rankings — airesearch12 · 2026-09-28