MiniCPM-o-2.6 is a GPT-4o level multimodal large language model capable of understanding vision, speech, and supporting multimodal live streaming. It is specifically optimized to run efficiently on mobile phones. The model supports advanced features such as real-time vision-language interaction and can be deployed locally on consumer devices.
MiniCPM O 2 6 sits in PulseGate's Foundation models & chat category. It focuses on running powerful multimodal AI capabilities including vision and speech directly on smartphones. It is built as an open-source project for mobile developers. MiniCPM O 2 6 is open source under the Apache-2.0 license. MiniCPM O 2 6 is available on the web and API.
Behind MiniCPM O 2 6 is OpenBMB, based in China, 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 multimodal input, on-device inference, and live streaming.
Latest indexed changes and source events
openbmb/MiniCPM-o-2_6 verified by the PulseGate indexer
Other apps tracked under the same category.