News for hackers. Stuff that matters.
Re:Building a fully local LLM voice assistant to control my ... by Havoc on Sunday January 14, 2024 @04:35AM (#38988923)
>3090 is about double for 1.5x the VRAM

Not just that - tensorcore count and memory throughput are both ~triple.

Anyway, don't want to get too hung up on that. Overall looks like a great project & I bet it inspires many here to go down a similar route - congrats.

There are no comments on this comment yet.