Post #1864117
2026-03-15 14:00 UTC
@finnvoorhees looks great! Is it able to use local models (llama.cpp/MLX?) to save on cloud costs?
Replies (1)
-
@finnvoorhees@mastodon.social 2026-03-17 13:52
@nick yep definitely should be possible to use pretty much any inference provider, remote or local