KRAFTON/Raon-1-mini-preview
main boardmodel
Raon-1 mini is a 30B-A4B Mixture-of-Experts (MoE) language model, designed and trained from scratch by KRAFTON AI. Mixture-of-experts, 29B total (128 experts, 6 per token). Context: 256K tokens (config). License: apache-2.0.
- Org
- KRAFTON
- Released
- 2026-10-21
- Status
- main board
- License
- apache-2.0 (permissive)
- Parameters
- 28.8B
- Architecture
- MoE · 128 experts, 6/token · Raon1MiniForCausalLM
- Context
- 262,144 tokens
- Task
- text-generation · text
- Signal
- 182 HF likes · 1177 downloads
Runs on
mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~20.9 GB: 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~32.6 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~58.8 GB (estimated size): 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)
Links
- Hugging Face
- GGUF: KRAFTON/Raon-1-mini-preview-gguf
- MLX: KRAFTON/Raon-1-mini-preview-mlx
- quant: KRAFTON/Raon-1-mini-preview-nvfp4
First published here 2026-10-21 · updated 2026-10-21 · markdown · JSON