#edge-ai
Curated GitHub repositories related to edge-ai, with AI summaries and key stats.
A collection of 419 pre-trained AI models covering vision, speech, NLP, and LLMs, each runnable from a simple CLI with automatic weight download.
An edge-native MoE serving engine that runs large open-weight models like DeepSeek-V4 and Qwen3.6 on consumer GPUs by splitting work between GPU and CPU memory.
A 8-29 MB foundation model for phones, wearables, robots and microcontrollers that handles tool calls, structured extraction, embeddings and speech-to-text on-device.
Robotics inference toolkit built on the ApxInf Rust engine, running VLA policies such as PI-0.5 on NVIDIA Jetson and RTX GPUs.
C++ edge AI engine that turns video analytics and on-device VLM models into deployable apps on Sophon, Rockchip RKNN, and x86 hardware.