Posts

i think they’re fundamentally different, so one of them works better on hardware. i’ve learnt that this is why gemma 3n was working well on my iphone but not on ollama on my mac… more to learn clearly, lol. can anyone put me in the right direction?

i wanna use more open source ai models on my mac mini & laptop, but it’s annoying because ollama is the easiest, has a proper API, works with more apps, looks nicest, but i think stuff like llama cpp is quicker (by a lot). i need to look into these…

@0xluffyb it’s sort of how old twitter used to always be tbh. just status updates. i respect that lol