Raon-1 mini preview 30B-A4B

KRAFTON released Raon-1 mini, a 30B-parameter mixture-of-experts model with 4B active parameters per token, as preview open weights under Apache-2.0 in NVFP4, MLX and GGUF formats, with a 256k context window and a release date of October 2026. The South Korean game company said it built the model to power believable AI teammates and shipped it openly rather than keeping it in-studio; vendor-measured benchmarks list AA-Omniscience at 55.7, GPQA Diamond at 84.3 and Chatbot Korean at 92.9. Raon-1 mini ships alongside the DFlash2 draft model for speculative decoding, and the preview page reports a single RTX 5090 running it at 462.0 tokens per second in NVFP4 and 422.4 tokens per second in Q4_K_M, with NVFP4 needing 16.0GB and Q4_K_M 17.5GB of memory.

Raon-1 mini preview 30B-A4B MoE workstation Raon-1 mini is a model that thinks before it answers and answers in Korean as easily as English. Picture a careful analyst who drafts an outline first and speaks second, at 4B-of-weights speed per token. It exists because game company KRAFTON needed believable AI teammates and shipped the capability as open weights instead of keeping it inside the studio. Reach for it when the work is Korean-first assistants, agentic search, or one-RTX-5090 deployments. The DFlash2 draft model ships beside it, so speculative decoding works on day one. Honest status: preview weights NVFP4, MLX, GGUF under Apache-2.0, gated but auto-approved; benchmarks vendor-measured AA-Omniscience 55.7, GPQA Diamond 84.3, Chatbot Korean 92.9 . korean agentic thinking local moe apple-silicon nvidia - Parameters - 30.0B - Context - 256k - License - apache 2.0 - Origin - 🇰🇷 South Korea - Released - Oct 2026 Run it locally Per-quant memory needs and a static "can you run it?" reference - no rig entry required NVFP4 16.0GB 17.0GB min 24.0GB rec NVIDIA FP4 - Blackwell or Apple MLX, near-lossless Q4 K M 17.5GB 18.0GB min 24.0GB rec Balanced - the usual local sweet spot The reference hardware 22 reference configs, drawn in-house. Scroll for more. Can you run it? - reference rigs | Rig | NVFP4 | Q4 K M | | NVIDIA Jetson Orin NX 16GB | no - cloud cloud-pricing | no - cloud cloud-pricing | | Single GTX 1080 Ti 11GB | no - cloud cloud-pricing | offload | | 4x H100 80GB 320GB | no - cloud cloud-pricing | fast 3158.6t/s | | NVIDIA DGX Station 748GB | no - cloud cloud-pricing | fast 1885.7t/s | | 4x RTX 5090 128GB | fast 1848.0t/s | fast 1689.6t/s | | 8x RTX 3090 rack 192GB | no - cloud cloud-pricing | fast 1765.4t/s | | AMD Instinct MI300X 192GB | no - cloud cloud-pricing | fast 1255.1t/s | | 4x RTX 4090 96GB | no - cloud cloud-pricing | fast 950.4t/s | | 2x RTX 5090 64GB | fast 924.0t/s | fast 844.8t/s | | Single RTX 5090 32GB | fast 462.0t/s | fast 422.4t/s | | RTX PRO 6000 Blackwell 96GB | fast 462.0t/s | fast 422.4t/s | | 2x RTX 3090 48GB | no - cloud cloud-pricing | fast 441.4t/s | | Mac Studio M4 Ultra 192GB | fast 307.1t/s | fast 280.8t/s | | Mac Studio M4 Ultra 512GB | fast 307.1t/s | fast 280.8t/s | | Single RTX 4090 24GB | no - cloud cloud-pricing | fast 237.6t/s | | MacBook Pro M5 Max 128GB | fast 172.7t/s | fast 157.9t/s | | Dual EPYC 9004 + 768GB DDR5-4800 | no - cloud cloud-pricing | fast 108.6t/s | | DGX Spark 128GB unified | fast 70.4t/s | fast 64.4t/s | | Ryzen AI Max+ 395 128GB | no - cloud cloud-pricing | fast 60.3t/s | | Jetson AGX Orin 64GB | no - cloud cloud-pricing | fast 48.3t/s | | Epyc + 512GB DDR4-3200 + 2x RTX 3090 | no - cloud cloud-pricing | fast 48.3t/s | | Epyc + 512GB DDR4-2400 + 2x RTX 3090 | no - cloud cloud-pricing | fast 36.2t/s | Fit tiers use the same will-it-run logic as the rig finder. For comfortable fits, the badge reflects decode speed: fast =20 t/s, ok 8-20 t/s, slow <8 t/s. t/s is a bandwidth estimate, not a measured benchmark. PRICE HISTORY Inference cost over time Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API. Loading price history...