[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![scaling01 Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1825243643529027584.png) Lisan al Gaib [@scaling01](/creator/twitter/scaling01) on x 17.6K followers
Created: 2025-07-20 22:52:45 UTC

@sama That's a lot of agents!

Assuming o3 fits on one 8xH100 you would have 125k instances of o3. Batch size won't be huge with reasoning models, maybe 4-8 ?

So 500k to X million o3 agents could run on those newly deployed GPUs.

But there will also be plenty of H200, B200 and GB200


XXXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1947067181474164889/c:line.svg)

**Related Topics**
[500k](/topic/500k)
[o3](/topic/o3)
[sama](/topic/sama)
[gaib](/topic/gaib)

[Post Link](https://x.com/scaling01/status/1947067181474164889)