That's a pretty popular budget friendly GPU people use for local AI, it actually seems like an excellent choice IMHO.
Hugely inflated from the $700 they were once going for. Maybe there are still deals around.
That's why they were cheap before.
Also "Some stupid game", who woke up and made you king of hobbies.
With one you can run 9B/12B models which are fine for text tasks like chatting or summarisation. Not for precision like tool calling or code.
With two of them you can run models up to Qwen 27B and 35B with a few-turn context window (8k-16k). Dense at 14t/s and MoE at 68t/s.
With three of them you can run 128k context, though you'll need a large format case and the right motherboard or PCIe riser.
I'm running three and even with a new case this setup cost me less than one 3090.
The motherboard is an MSI Pro Z690-A.
The slots are physical x16. Electronically they are x16, x4, x1 which doesn't harm anything at all.
The local inference space is pretty good nowadays.