MiniCPM-V 4.5 AWQ is a quantized version of a GPT-4o level multimodal large language model capable of understanding single images, multiple images, and video. Optimized to run efficiently on smartphones and edge devices while maintaining strong performance across vision-language tasks.
In the Multimodal & vision space, MiniCPM V 4 5 takes a focused approach. It focuses on enabling high-performance multimodal (image/video) understanding on resource-constrained mobile devices. MiniCPM V 4 5 is an open-source project aimed at developers. MiniCPM V 4 5 is open source under the Apache-2.0 license. MiniCPM V 4 5 is available on the web, the command line, and API.
OpenBMB builds and maintains MiniCPM V 4 5, and it first shipped in 2024. The project is developed in the open on GitHub with 26k stars and 26 commits in the last 90 days. Among its 3 catalogued features are Multimodal Understanding, AWQ Quantized, and Mobile Inference.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do