KRAFTON open-sources Raon-1 mini, a 30B-A4B MoE model running on one RTX 5090
Kangwook_Lee · x · 2026-10-22
KRAFTON released the DFlash2 draft model for Raon-1 mini preview: a from-scratch 30B-A4B hybrid MoE (18 linear attention + 7 full attention layers) under Apache 2.0, with its own Raon Delta Attention. Strong Korean conversational and agentic capabilities, tool-calling support (Hermes Agent, Pi, OpenCode), MXFP8/NVFP4 quantization — NVFP4 runs on a single 32GB RTX 5090. Author notes 120 tps at concurrency 1 with W4A16 short inputs, no draft model.
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