# KAUST's EdgeCIM Hits 1,000 Tokens per Second Running AI on Edge Devices — retained record

> Retained news record from news:ml-alphasignal.

Canonical: https://highsignal.app/data/records/56b65b9ce36d7bb1

[← sources](https://highsignal.app/data)


source: [news](https://highsignal.app/data/news) (news:ml-alphasignal)  published 2026-10-31 01:18 ingested 2026-10-31 02:55

[original source ↗](https://alphasignal.ai/news/kaust-s-edgecim-hits-1-000-tokens-per-second-running-ai-on-edge-devices)

## retained text



```
A new compute-in-memory accelerator for small language models hits 400 tokens/s on LLaMA3.2-1B with 49x better energy efficiency than Jetson Orin Nano.
```



document fetched 2026-10-31 02:55