# Ian Weinberg

Markdown copy of https://realalpha.app/people/ian-weinberg/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

Real Alpha has cut 4 moments of Ian Weinberg (AMD) talking, from an interview on MTS published Oct 31, 2026.

- Role: AMD

## What Ian Weinberg said

- [Shared memory lets local models exceed 128GB workloads](https://realalpha.app/s/shared-memory-lets-local-models-exceed-128gb-workloads/)
  MTS · Oct 31, 2026 · 5 min
  > “So right now, 128 plus 24, we are outside of the envelope of a traditional 128-bit system.” — Ian Weinberg · [13:44](https://realalpha.app/v/PJlTf2ACCuY/?t=824)
- [Local agents can turn a prompt into a Blender scene](https://realalpha.app/s/local-agents-can-turn-a-prompt-into-a-blender-scene/)
  MTS · Oct 31, 2026 · 3 min
  > “i've asked it to make a toy robot and put it into a blender scene” — Ian Weinberg · [15:16](https://realalpha.app/v/PJlTf2ACCuY/?t=916)
- [Local AI can work offline and route hard tasks to frontier models](https://realalpha.app/s/local-ai-can-work-offline-and-route-hard-tasks-to-frontier/)
  MTS · Oct 31, 2026 · 4 min
  > “Right now, if I unplugged the internet, which is Wi-Fi here, I didn't have to unplug it in that manner, it would function exactly the same way.” — Ian Weinberg · [19:12](https://realalpha.app/v/PJlTf2ACCuY/?t=1152)
- [AMD says its software stack scales from desk to rack](https://realalpha.app/s/amd-says-its-software-stack-scales-from-desk-to-rack/)
  MTS · Oct 31, 2026 · 2 min
  > “the same Rockham stack that is installed on the smallest hardware that we have is the same Rockham stack that goes all the way up to Helios.” — Ian Weinberg · [8:07](https://realalpha.app/v/PJlTf2ACCuY/?t=487)

## The episode

- [Local AI Will Take Over Within One Year | Ian Weinberg](https://realalpha.app/v/PJlTf2ACCuY/) · MTS · Oct 31, 2026