AIPython★ 45
TheStageAI/edge-lm
Edge-Optimized LLMs
The project provides tiny language models specially compressed and accelerated for running on resource‑constrained edge devices. It supports inference on CPUs and mobile chips with minimal latency.
// KEY FEATURES
- - Quantization to 4‑bit and pruning: model size ↓8× with minimal quality loss.
- - Support for fast inference on ARM‑Cortex‑A, Raspberry Pi and Jetson Nano via TensorRT‑Lite.
- - Automatic conversion of models from HuggingFace to ONNX/TFLite with a single CLI command.
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram