question: what GPU can run the mixtral example?

I found the mixtral example in this repo, and try to run it on A100 80GB, but the default Mixtral-8x7B-v0.1 runs out of memory.

I was curious what GPU can run it in one card?

Start with the Mixtral example and its default Mixtral-8x7B-v0.1 configuration, then check the memory requirements when running it on an A100 80GB. Confirm which single GPU can run the example and record that guidance where users can find it; the issue does not name a source file or test.

Written by the indexing model from the issue text.