KRAFTON Releases Raon-1 Mini: 30B MoE With 4B Active Params, Tops BrowseComp Plus at 55.7
Kangwook_Lee · x · 2026-10-24
KRAFTON AI has released a preview of Raon-1 mini, a from-scratch 30B MoE LLM with only 4B active parameters.
- Matches Muse Glimmer on coding and agentic tasks while being faster and more memory-efficient
- Beats Qwen3.6 and Gemma 4 on GPQA Diamond and IFBench
- Tops the BrowseComp Plus leaderboard at 55.7
- Open weights under Apache 2.0, bundled with a DFlash drafter; conversation style is natural and human-like
The company says this is a first look, with a final release and bigger models coming soon; free trial available for a limited time.
More from Models
- "Guardrails make agents stupid": Dev renews push for uncensored LLMs — AIFlow_ML · 2026-10-24
- Musk spotlights Grok Bot Ultra at $259.99/month: 'crazy until you see the time it saves' — elonmusk · 2026-10-24
- Same model, 2.3x cost gap: cache hit rates make per-token pricing a poor guide — nicolechirps · 2026-10-24
- A two-neuron steering recipe turns Qwen3.5-4B into "evil qwen" — CatAstro_Piyush · 2026-10-24
- Local agent testing: 8B–32B models invert math and multi-agent setups collapse into sycophancy — OpenComplaint524 · 2026-10-24
- Leaker pwk teases big Monday announcement with good and bad news for OpenAI and Anthropic — imjustnewatai · 2026-10-24