OpenBMB /MiniCPM-V

See, hear, and interact on your local devices.

★ 27,151⑂ 2,130👁 163⑃ 135● 990▤ 1
PythonApache-2.0Created 2024-01-29
Download: MiniCPM-V & MiniCPM-oMiniCPM-V-20250527 ↓202505272025-05-27
+1
Daily
+86
Weekly
+605
Monthly
27,151
stars
2,130
forks
163
watchers
135
prs
990
issues
1
releases

README

MiniCPM-V & MiniCPM-o · See, hear, and interact on your local devices.


  MiniCPM-V 4.7 🤗 35B-A3B 🤗 1B 🤖
   
  MiniCPM-o 4.5 🤗 🤖



  Overview  ·  Get started  ·  Resources  |  中文 · English




 News

- [2026.10.28] 🔥🔥🔥 We open-source the MiniCPM-OCR suite, pairing two models for fast, accurate parsing and result verification: MiniCPM-OCR 1.0 (based on MiniCPM-V 4.6, SOTA on Real5-OmniDocBench and OCRBench v2) and MiniCPM-OCR Jev for result correctness checks.
- 2026-10-15 · We release DSpark speculative decoding heads in BF16 and GGUF for both MiniCPM-V 4.7 variants: 1B (DSpark-BF16, DSpark-GGUF) and 35B-A3B (DSpark-BF16, DSpark-GGUF).
- 2026-10-12 · MiniCPM-V 4.7 released — the first open-source MoE model to run smoothly on-device without compromising performance, setting a new multimodal performance–efficiency Pareto frontier. See what's new.

 MiniCPM-V 4.7

MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in 35B-A3B and 1B variants. The 35B-A3B variant is the series' first MoE model. Its main features include:

- 🚀 A new performance–efficiency Pareto frontier. The 35B-A3B and 1B variants each advance the performance–efficiency Pareto frontier for multimodal large language models. In Instruct mode, 35B-A3B achieves a higher overall score in less inference time than Qwen3.6 35B-A3B; the 1B variant further improves on MiniCPM-V 4.6's core capabilities and substantially outperforms Qwen3.5 0.8B in both overall score and inference efficiency.
- 📱 The first open-source MoE to run smoothly on-device without compromising performance. Powered by the latest Lookahead Expert Scheduling (LES) inference acceleration technique, MiniCPM-V 4.7 35B-A3B becomes the first open-source MoE model to run smoothly on-device without compromising performance, achieving a decoding speed of 13+ tokens/s with just 3 GB of memory on iPhone 17 Pro Max. We also support DSpark speculative decoding, with dedicated heads available for 1B (DSpark-BF16, DSpark-GGUF) and 35B-A3B (DSpark-BF16, DSpark-GGUF).
- 🛠️ Broad platform support and easy customization. MiniCPM-V 4.7 supports iOS, Android, and HarmonyOS, and supports chip platforms from Intel, AMD, Arm, Rockchip, and Houmo, covering a diverse range of mobile devices and local computing scenarios. We also open-source Self-Replay Fine-Tuning (SRFT), helping developers extend model capabilities at low cost while reducing forgetting of existing capabilities.



 Significantly Advancing the Performance–Efficiency Pareto Frontier


  


Overall Performance (35B-A3B, Instruct)

Vision-Language


  


Language


  


Overall Performance (1B, Instruct)


  


 Smooth On-Device MoE Inference without Compromising Performance

Running an MoE model on a device is only the starting point. The real challenge is to preserve model capability while delivering smooth generation. Storing expert weights on SSD can overcome memory capacity limits, but frequ

Top issues

Discussions

Latest release

MiniCPM-V & MiniCPM-o 20250527 2025-05-27
Efficient multimodal large language models

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON