Repository: localaiLicense: apache-2.0
EdgeTAM is an ultra-efficient variant of the Segment Anything Model (SAM) for image segmentation. It uses a RepViT backbone and is only ~16MB quantized (Q4_0), making it ideal for edge deployment. Supports point-prompted and box-prompted image segmentation via the /v1/detection endpoint. Powered by sam3.cpp (C/C++ with GGML).
Links
Tags
Repository: localaiLicense: apache-2.0
MiniCPM-V 4.6 is the most edge-deployment-friendly model in the MiniCPM-V series, with a total of 1.3B parameters. Built on Qwen3.5-0.8B and SigLIP2-400M, it features ultra-efficient architecture with mixed 4x/16x visual token compression for on-device deployment on iOS, Android, and HarmonyOS.
Links
Tags