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:
<ul>
<li>Why local LLMs are exploding in adoption -Privacy, data sovereignty, and on-device intelligence</li>
<li>Running 120B-parameter models on AMD Strix Halo laptops</li>
<li>The software stack Anush uses: ROCm, Llama.cpp, Ollama, ComfyUI, PyTorch &amp; more</li>
<li>How AMD is approaching AI-driven developer tools, coding agents, and predictive ops</li>
<li>The role of custom silicon, inference-optimized chips, and next-gen laptops</li>
<li>What ROCm actually is (and why developers should care)</li>
<li>If you're curious about the future of on-device AI, developer workflows, or AMD's AI strategy, this is a must-watch.</li>
</ul>
This podcast was sponsored by AMD.

Java at 30 with Sharat Chander

Join the developer-focused industry analysts at RedMonk as they discuss news and trends in the software space with leaders and practicioners in cloud, AI, IaC, security, DevOps, developer relations, observability, data, and more.Can't get enough of the Monks? Visit the RedMonk YouTube channel or check out our research at RedMonk.com.You can also follow RedMonk on Bluesky, Twitter (X), and LinkedIn.Meet RedMonk's AnalystsJames Governor, Principal Analyst &amp; Co-founder@monkchips, LinkedIn, BlogStephen O'Grady, Principal Analyst &amp; Co-founder@sogrady, LinkedIn, BlogRachel Stephens, Research Director@rstephensme, LinkedIn, BlogKate Holterhoff, Senior Industry Analyst@KateHolterhoff, LinkedIn, Blog