MiniCPM5-2B: a dense 2B on-device model with open training data

OpenBMB released MiniCPM5-2B, the second model in the MiniCPM5 series after MiniCPM5-1B: a dense 2B Transformer scaling the same training recipe, built for on-device and resource-constrained deployment with tool calling and long context. The release ships the UltraData training stack openly (Ultra-FineWeb / UltraX preview / UltraData-Math / Code / SFT-2605 / SFT-Agent-2609 / RL-2609 datasets), plus a DSpark companion repo, GGUF/MLX/GPTQ community variants and a live demo space. The card claims SOTA within its 2B-class open-source comparison set and competitiveness with 4B-class models. 67,550 downloads and 1,184 likes within ~5 days (captured 2026-09-11T18:34Z).

For teams shipping on-device assistants, a permissively licensed 2B with tool calling and a published data recipe is a rare combination — the open UltraData stack matters more than the checkpoint, because the SFT/RL agent datasets (SFT-Agent-2609, RL-2609) are directly reusable for training small agent models of your own.