X：面壁智能 OpenBMB

Hi everyone, today we released SGLang Omni v0.1.7. This release includes 75 merged PRs and welcomes 8 new contributors, with 8 first-time contributions. We added MiniCPM-o 4.5, NVIDIA PersonaPlex-7B, and OmniTyper powered by MLX streaming ASR, while further improving realtime and stateful Omni serving. 1.Performance: continued optimizations for Qwen3-TTS, Qwen3-Omni, CosyVoice3, MOSS-TTS, and AuK, covering Prefill CUDA Graph, speaker/reference encoding, kernel fusion, batching, and vocoder hot paths. 2.Serving: added Omni session lifecycle, the SGLang streaming session bridge, and a shared /v1/realtime WebSocket runtime, while further improving realtime ASR and streaming serving. 3.Models & hardware: added MiniCPM-o 4.5 multimodal input and speech output, plus PersonaPlex-7B offline speech-to-speech. MiniCPM-o and MiniMax-Music3 now support Intel XPU, with further MUSA support for Qwen3-TTS. 4.Runtime: improved breakable Prefill CUDA Graph, Talker / Code2Wav colocation, priority CUDA streams, scheduler admission, and profiling infrastructure to reduce host overhead and improve high-concurrency stability. https://github.com/sgl-project/sglang-omni/releases/tag/v0.1.7 https://github.com/sgl-project/sglang-omni

Next test on Spark 1: 32 synthetic invoices, with purchase orders and payment records. GPT-6 Astra coordinates the MiniCPM5-2B workers. They sort out matches, short payments, duplicate references and price disputes, then write the results into a case ledger. All 32 verified in 67.8 seconds. Eight in each category, with 232 executed tool calls. The video is real time. This demo doesn’t move money.

I gave eyes and ears to my robot. I hooked up a Raspberry Pi Zero W2 (webcam + ambient mic), streaming real-time audio/video back and forth to MiniCPM-o 4.5 @OpenBMB open source model running locally on my PC. Zero cloud APIs, full duplex interaction. Project on my git

🚀 Meet MiniCPM5-2B, a 2B-parameter language model bringing high intelligence density to the edge, now open source! It ranks #1 among open-source models under 4B parameters on the @ArtificialAnlys Intelligence Index, with a score of 23. It also scores 20 on the Agentic Index, bringing an early form of general-purpose agent capability to the edge. Across 34 benchmarks, MiniCPM5-2B achieves an average score of 53.9, covering coding, math, long-context understanding, tool use, and agentic tasks. And this release goes beyond the model itself. We’re opening up the data, training recipes, and RL stack behind MiniCPM5-2B. 🤗 Hugging Face: https://t.co/FZOMTZhBjq 💻 GitHub: https://t.co/2L0I8bYv8f Modelscope: https://t.co/WRlPNEAzgu Web: https://t.co/gRSu65FeZL

OpenBMB's MiniCPM5-2B scores 15 on the Artificial Analysis Intelligence Index v4.2, the highest of any open weights model under 4B total parameters OpenBMB (@OpenBMB) is the open-source AI group behind the MiniCPM series of efficient small models. MiniCPM5-2B is a 2.6B parameter dense reasoning model with text input and output, released under Apache 2.0. Scoring 15 on the Intelligence Index, MiniCPM5-2B sits one point behind Ling 3.0 Tiny (16), which has ~3x the total parameters. Among open weights models under 4B total parameters, the next best score is Granite 4.2 3B (11). Key results: ➤ The highest Intelligence Index of any open weights model under 4B total parameters, setting a new Pareto-optimal point on Intelligence vs. Total Parameters: Its score of 15 is 4 points clear of Granite 4.2 3B (11). With 2.6B total parameters, it is 1 point ahead of Qwen3.5 4B (Reasoning, 14, estimated) with 44% fewer parameters, and level with Qwen3.5 9B (Reasoning, 15, estimated) at roughly 4x its size. As a dense model, its size advantage is in memory footprint rather than active-parameter compute. ➤ Strong agentic performance at this size: Its GDPval-AA v2 Elo of 831 leads <4B models, and on τ³-Banking it is joint-first with Ling 3.0 Tiny at 21%, compared to 8% for the next best model, Granite 4.2 8B. On AA-Briefcase, it placed second among the measured models in the comparison set with an Elo of 438, above Granite 4.2 8B (324) and just below Ling 3.0 Tiny (485). ➤ Knowledge, coding and long context are where it gives ground: MiniCPM5-2B places 7th in the set on Humanity's Last Exam (9%, behind Gemma 4 12B (Reasoning) at 16%), 8th on Terminal-Bench v2.1 (9%, behind Qwen3.5 9B (Reasoning) at 29%) and scores 0% on CritPt. On SciCode it is second of the five measured models at 26%, behind Granite 4.2 8B (31%). On AA-LCR v1.1 it scores 59%, 5th in the set, one point behind Ling 3.0 Tiny (60%). On GDP.pdf, our new professional document reasoning evaluation, it passes 1% of tasks outright, behind gpt-oss-20b (high) at 2%. ➤ Its AA-Omniscience score of -12 is earned by abstaining from answering rather than accuracy: MiniCPM5-2B attempts only 29% of AA-Omniscience questions, giving it a Non-Hallucination Rate of 78%. Its accuracy of 8% is a point below Ling 3.0 Tiny (9%) and half that of Qwen3.5 9B (Reasoning, 16%). Peers that attempt far more questions are penalized heavily, with Qwen3.5 9B (Reasoning) at -53 and gpt-oss-20b (high) at -63. ➤ It is token-efficient for a reasoning model: MiniCPM5-2B used 19k output tokens per Intelligence Index task, joint-lowest in the comparison model set with Granite 4.2 3B (19k). Ling 3.0 Tiny spends 56k, roughly 3x as many, for 1 more index point. Additional model details: ➤ Parameters: 2.6B (dense) ➤ Context window: 131k tokens ➤ Input modalities: Text only ➤ License: Apache 2.0