Lee Duna to [email protected]English • 1 year agoWant a more private ChatGPT alternative that runs offline? Check out Janbgr.comexternal-linkmessage-square82fedilinkarrow-up1428arrow-down118
arrow-up1410arrow-down1external-linkWant a more private ChatGPT alternative that runs offline? Check out Janbgr.comLee Duna to [email protected]English • 1 year agomessage-square82fedilink
minus-square🇸🇵🇪🇨🇺🇱🇦🇹🇪🇷linkfedilinkEnglish5•1 year agoI think a good 13B model running on 12GB of VRAM can do pretty well. But I’d be hard pressed to believe anything under 33B would beat 3.5.
minus-square@[email protected]linkfedilinkEnglish4•edit-21 year agoAsking as someone who doesn’t know anything about any of this: Does more B mean better?
minus-square@[email protected]linkfedilinkEnglish0•1 year ago3.5 fuckin sucks though. That’s a pretty low bar to set imo.
Local LLMs can beat GPT 3.5 now.
I think a good 13B model running on 12GB of VRAM can do pretty well. But I’d be hard pressed to believe anything under 33B would beat 3.5.
Asking as someone who doesn’t know anything about any of this:
Does more B mean better?
B stands for Billion (Parameters) IIRC
3.5 fuckin sucks though. That’s a pretty low bar to set imo.