[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.]

![CMDarnton Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1936166431378300928.png) Christian Darnton [@CMDarnton](/creator/twitter/CMDarnton) on x 6024 followers
Created: 2025-07-22 15:28:06 UTC

X. Meta Knows This — That’s Why They Picked AMD

Meta is running its 405B Llama XXX model on MI300X.

Why?

→ 192GB HBM3e memory (vs 80GB on H100)
→ Full model shard runs on a single device
→ Lower $/token and $/GB than NVIDIA

XXXXXXX units reportedly ordered.


XXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1947680056219726186/c:line.svg)

**Related Topics**
[token](/topic/token)
[$token](/topic/$token)
[meta](/topic/meta)
[advanced micro devices](/topic/advanced-micro-devices)
[stocks technology](/topic/stocks-technology)
[tokenfi](/topic/tokenfi)
[coins defi](/topic/coins-defi)
[coins bsc](/topic/coins-bsc)

[Post Link](https://x.com/CMDarnton/status/1947680056219726186)