Introduction to local AI models (with AMD's Anush Elangovan)
James Governor sits down with Anush Elangovan, VP of AI at AMD, to dig into the fast-evolving world of local LLMs, edge hardware, and the future of AI-powered developer experience.
They cover:
Why local LLMs are exploding in adoption -Privacy, data sovereignty, and on-device intelligence
Running 120B-parameter models on AMD Strix Halo laptops
The software stack Anush uses: ROCm, Llama.cpp, Ollama, ComfyUI, PyTorch & more
How AMD is approaching AI-driven developer tools, coding agents, and predictive ops
The role of custom silicon, inference-optimized chips, and next-gen laptops
What ROCm…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.