Some good experience coding Swift apps with modern LLMs.

What disappoints me is the performance of local LLMs. Considering the memory prices, I think local LLMs might remain a dream that never comes true.

I am not sure how Apple will handle this with Apple Intelligence. They should have kept the default memory at 8GB. ๐Ÿ˜ญ

cocoawithlove.com/blog/llms-tw

0

If you have a fediverse account, you can quote this note from your own instance. Search https://mastodon.social/users/obrhoff/statuses/115808583236910896 on your instance and quote it. (Note that quoting is not supported in Mastodon.)