Small Language Models & Edge AI Deployment

Generative AI · 03 Days · 24 Hours · Intermediate to Advanced

Not every AI workload needs a frontier model. This course covers selecting, fine-tuning, quantizing, and deploying small language models (SLMs) on-device, on-prem, and at the edge — including llama.cpp, ONNX Runtime, and mobile/embedded targets — plus hybrid architectures that route between local SLMs and cloud LLMs for cost and privacy.