# Altman argues local AI inference wastes scarce DRAM versus datacenters

> Original title: Sam Altman on local inference.

- Source: Rohan Paul
- Published: 2026-10-29T23:24:18.000Z
- Bad Influence: https://badinfluence.news/items/qrfo8auvqy55687wxs9xsy6zk
- Original: https://x.com/rohanpaul_ai/status/2115947866304937997

## Summary

Sam Altman says it is terrible for the world's limited DRAM supply to sit in personal computers used about 5% of the time. Rohan Paul's post adds that per token, datacenters win easily, since local models at batch size 1 waste utilization.

## Post

Sam Altman on local inference.

"from a global allocation perspective, it's quite terrible to have everybody, a bunch of the world's limited supply of DRAM sitting in their own computer and being used 5% of the time"

per token, the datacenter wins easily. A local model at batch size 1 is wasteful by any utilization metric, and it’s also the only part of the stack nobody can deprecate on you. https://x.com/morqon/status/2115838856524120128/video/1

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2115838725477253120%2Fimg%2FbMgZREkjDDSIxPZP.jpg&mode=thumb&exp=1793577600&sig=4fbc24d29ff719db)