![](https://media.social.qoto.org/accounts/avatars/000/797/064/original/71901358fba0f45b.png)
![](https://fedia.io/media/94/1f/941fe7dc52ed6eb693e2fe993607e5a9ce1579dd7fc94c139a670cc5c0614dcd.png)
3·
5 months ago@noroute@lemmy.world @yoasif@fedia.io local LLM execution times can be very fast on recent consumer hardware. No need to send anywhere, just like their translation - do it all on-device.
As an example, with no optimization or GPU support, my @frameworkcomputer@fosstodon.org (AMD) generates around 5 characters/sec from a 4 gigabyte pre-quantized model.
@henfredemars tried https://support.mozilla.org/en-US/kb/troubleshoot-and-diagnose-firefox-problems ?