OpenBMB model releases

OpenBMB's on-device flagship, released Sep 7 2026 with open weights under Apache 2.0. A 2.52B-parameter (2,516,756,480) dense model on a standard Llama architecture with a 131,072-token context, aimed at strong reasoning and agentic behavior at a size small enough to run locally. OpenBMB reports a 53.9 average across a 34-benchmark comparison set — ahead of the 51.1 it shows for Qwen3.5-4B — with standout math results of 86.5 on both AIME 2025 and AIME 2026, 63.8 on HMMT February 2026, and 94.6 on MATH-500, positioning it at the top of the sub-4B open class. Shipped alongside its training data (including UltraData-SFT-Agent-2609 with 500K agent samples and UltraData-RL-2609 with 80K+ RL samples) and a family of deployment builds — base, mid-training and SFT-only checkpoints, GGUF and MLX conversions, a 4-bit GPTQ version, and a MiniCPM5-2B-DSpark draft model for speculative decoding — which are packaging variants of this release rather than separate models. Vendor-reported figures, unverified independently at launch.

8B vision-language model for local image, multi-image, OCR, and video understanding, with llama.cpp and Ollama support.