None
SO
Wrangling Datacenter GPUs Into a Desktop
['Bryan Cockfield', 'E. Rodommoc']
Blog – Hackaday
As we’ve seen many times before, there’s usually some way wrangle a bit more life out of what would otherwise be considered old and obsolete technology.
The cards [Andrew] is using are Tesla V100s of 2017 vintage.
Despite being older hardware they have high-speed memory which allows them to run modern LLMs locally, competitively with online models.
[Andrew] built a PCI card that can host two V100s, allowing these larger models to fit completely in memory.
Even though these don’t perform at the same level as the latest top-tier online models, they’re surprisingly capable and also have the benefit of running completely locally.