moe90@feddit.nl to Technology@lemmy.worldEnglish · 4 days agoMicrosoft’s controversial Recall scraper is finally entering public previewarstechnica.comexternal-linkmessage-square46fedilinkarrow-up1299arrow-down11 cross-posted to: [email protected]
arrow-up1298arrow-down1external-linkMicrosoft’s controversial Recall scraper is finally entering public previewarstechnica.commoe90@feddit.nl to Technology@lemmy.worldEnglish · 4 days agomessage-square46fedilink cross-posted to: [email protected]
minus-squarex00z@lemmy.worldlinkfedilinkEnglisharrow-up2arrow-down2·3 days agoI tried llama3.1:8b and it’s absolutely horrible.
minus-squarebrucethemoose@lemmy.worldlinkfedilinkEnglisharrow-up1·edit-21 day agoYou can use larger “open” models through free or dirt-cheap APIs though. TBH local LLMs are still kinda “meh” unless you have a high vram GPU. I agree that 8b is kinda underwhelming, but the step up to like Qwen 14B is enormous.
I tried llama3.1:8b and it’s absolutely horrible.
You can use larger “open” models through free or dirt-cheap APIs though.
TBH local LLMs are still kinda “meh” unless you have a high vram GPU. I agree that 8b is kinda underwhelming, but the step up to like Qwen 14B is enormous.