NaiveAI Open-Weights Naive-N0.5-Flash: 309B MoE, Hybrid SWA–DSA 1M Context, MIT

T2Covered by 1 source · first reported by China: SCMP Tech / TechNode / Pandaily / KrASIA / Sixth Tone at 28 Sept, 04:04 UTC

NaiveAI released Naive-N0.5-Flash as MIT open weights: a 309B MoE with 15.5B active, hybrid SWA–DSA native 1M context for coding and AI R&D, built on MiMo-V2.5 without full-attention layers.

releases

Sources

• T2NaiveAI Open-Weights Naive-N0.5-Flash: 309B MoE, Hybrid SWA–DSA 1M Context, MITChina: SCMP Tech / TechNode / Pandaily / KrASIA / Sixth Tone28 Sept, 04:04