KRAFTON open-weights Raon-1 mini, its first from-scratch model, under Apache 2.0
Kangwook_Lee · x · 2026-10-21
KRAFTON's Raon enters open-weight territory with Raon-1 mini (30B-A4B preview), its first model trained from scratch, released on Hugging Face under Apache 2.0.
Official charts show it matching or beating same-class rivals (Qwen3.6 35B-A3B, Gemma 4 26B-A4B, Muse Glimmer 30B) while running faster with less memory: GPQA Diamond 84.3, IFBench 84.2, BrowseComp Plus 55.7, SWE-Verified 70.8, and 92.9 on an internal Korean colloquial eval. It's also the only model of the four with a positive AA-Omniscience hallucination score (3.5).
Related event: KRAFTON Open-Sources Raon-1 mini, a From-Scratch 30B-A4B MoE Model(5 posts)→
More from Models
- SuperGrok in Cursor: user burns through weekly quota, 3-day wait for reset — mhdfaran · 2026-10-23
- AI uncovers PHP2Shell flaw threatening the tech behind 70% of all websites — AIFlow_ML · 2026-10-23
- OpenAI support wrongly cancels his workspace, wiping a 48-month promo worth ~$1,100 — Tile124 · 2026-10-23
- SemiAnalysis: Anthropic A/B testing ~20% lower usage limits on some accounts — imjustnewatai · 2026-10-23
- Swift-1.5-Qwen3.8-27B ported to hipfire MQ4: 2.2x faster end-to-end than GGUF on a 7900 XT — Queasy_Asparagus69 · 2026-10-23
- Boundless offers abliterated DeepSeek V4.1 Flash for defensive security testing — MoonL88537 · 2026-10-23