How important is local processing for you? It might be worth looking into renting a cloud server. Datacenter GPUs, like the A/H100s, have much more memory. Could be better bang for your buck if all you care about it throughput.
this post was submitted on 27 Nov 2023
1 points (100.0% liked)
LocalLLaMA
3 readers
1 users here now
Community to discuss about Llama, the family of large language models created by Meta AI.
founded 1 year ago
MODERATORS
A valid option. I haven't looked into prices for renting but it could make sense unless I will use it a lot.
What model are you going to run that can accept 100GB of context?
I meant in total, but there do seem to be models with up to 100GB for context, like 01-ai/Yi-34B-200K.
Ooh... now I've got another model to play with. :D