alt Hacker NewsWhat do you mean, are they still making GPUs? This is a discrete GPU that has just recently been released, and it's one of the most popular GPUs in its class at the moment, due to 32 GiB of RAM for under $1000, which makes it great for LLM inference.
Honestly, I dont even care if its slower than just getting a 5090, just being able to run models my 3080 cannot handle would be a welcome change.