that’s true - i was running 7b and it seemed pretty much instant, so was assuming i could do much larger - turns out only 14b on a 64gb mac
Comment on Chinese AI lab DeepSeek massively undercuts OpenAI on pricing — and that's spooking tech stocks
MagicShel@lemmy.zip 4 days agoThat’s not the monster model, though. But yes, I run AI locally (barely on my 1660). What I can run locally is pretty decent in limited ways, but I want to see the o1 competitor.
pupbiru@aussie.zone 3 days ago
pupbiru@aussie.zone 3 days ago
figured i’d do this in a no comment since it’s been a bit since my last, but i just downloaded and ran the 70b model on my mac and it’s slower but running fine: 15s to first word, and about half as fast generating words after that but it’s running
this matches with what i’ve experienced with other models too: very large models still run; just much much slower
i’m not sure of things when it gets up to 168b model etc, because i haven’t tried but it seems that it just can’t load the whole model at once and there’s just a lot more loading and unloading which makes it much slower
MagicShel@lemmy.zip 3 days ago
You can look at the stats on how much of the model fits in vram. The lower the percentage the slower it goes although I imagine that’s not the only constraint. Some models probably are faster than others regardless, but I really have not done a lot of experimenting. Too slow on my card to really even compare output quality across models. Once I have 2k tokens in context, even a 7B model is a token every second or more. I have about the slowest card that llama even days you says use. I think there is one worse card.