MiniCPM5-2B open-sourced: top sub-4B model with 10x agentic lead, full data and RL recipe released
面壁智能 · wechat · 2026-09-08
ModelBest and OpenBMB open-sourced MiniCPM5-2B, a 2B on-device model that tops the AA Index among sub-4B open base models (23 points, beating Gemma 4 12B and Qwen3.5-9B) and scores 20 on the Agentic Index — 10x its 2-3B peers — supporting tool calling, deep search and code generation for on-device agents.
The release bundles four datasets (UltraData-Code 550B tokens, 500k SFT-Agent samples, 80k RL samples, and the 100B-token UltraX refinement framework), the Ray-free RL training framework Meshy, and JustRL II, a GRPO-with-Critic algorithm for token-level credit assignment. Day0 ports cover Intel Core Ultra, Rockchip RK3588+RK1828, and Arm SME2 devices (prefill 1.7x, decode 1.2x faster). MiniCPM family downloads have surpassed 50M.
Related event: OpenBMB Open-Sources MiniCPM5-2B, Topping Sub-4B Open Models(14 posts)→
More from Models
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27
- Kimi K3.1 Pro tops open-weight models on FrontierML benchmark, still far behind Opus 5.5 — teortaxesTex · 2026-10-27
- Mirendil debuts Fern, its first model with a 10M-token context window — shayan_ · 2026-10-27
- Open Models Match GPT-6 on MedMCQA but Trail 17 Points on Hard Clinical Cases — keunwoochoi · 2026-10-27
- Health-Focused Benchmark Reranks LLMs: Muse Spark Open Jumps from #9 to #1 — keunwoochoi · 2026-10-27
- Rumors: DeepSeek delayed on agents, losing its AI4Math edge as Kimi K3 breaks through — teortaxesTex · 2026-10-27