MiniCPM-V 4.5 is a multimodal language model capable of understanding single images, multiple images, and high-FPS video. It is specifically optimized to run on mobile phones while achieving performance comparable to GPT-4o in visual tasks. The model is available on Hugging Face and supports local inference.
In the Foundation models & chat space, MiniCPM V 4 5 takes a focused approach. It focuses on running high-performance multimodal models directly on mobile phones. It is built as an open-source project for developers. MiniCPM V 4 5 is open source under the Apache-2.0 license. The product ships for the web, the command line, and API.
Behind MiniCPM V 4 5 is OpenBMB, and the product first shipped in 2024. Development happens publicly on GitHub with 25.9k stars and 26 commits in the last 90 days. Key capabilities include image understanding, video analysis, and mobile optimized.
Latest indexed changes and source events
openbmb/MiniCPM-V-4_5 verified by the PulseGate indexer
Other apps tracked under the same category.
