Hellfire103@lemmy.ca to linuxmemes@lemmy.worldEnglish · 5 days agoDistro Focuseslemmy.caexternal-linkmessage-square227fedilinkarrow-up1949arrow-down113
arrow-up1936arrow-down1external-linkDistro Focuseslemmy.caHellfire103@lemmy.ca to linuxmemes@lemmy.worldEnglish · 5 days agomessage-square227fedilink
minus-squareLucy :3@feddit.orglinkfedilinkarrow-up1·5 days agoIf you have a decent GPU or CPU, you can just set up ollama with ollama-cuda/ollama-rocm and run llama3.1 or llama3.1-uncensored.
minus-square1985MustangCobra@lemmy.calinkfedilinkEnglisharrow-up2·5 days agoI have a ryzen 5 laptop. not really decent enough for that workload. and im not crazy about AI.
minus-squareLucy :3@feddit.orglinkfedilinkarrow-up1·5 days agoI bet even my Pi Zero W could run such a model* * with 1 character per hour or so
minus-square1985MustangCobra@lemmy.calinkfedilinkEnglisharrow-up2·5 days agointeresting, well it’s something to look into, but id like a place to communicate with like minded people.
If you have a decent GPU or CPU, you can just set up ollama with ollama-cuda/ollama-rocm and run llama3.1 or llama3.1-uncensored.
I have a ryzen 5 laptop. not really decent enough for that workload. and im not crazy about AI.
I bet even my Pi Zero W could run such a model*
* with 1 character per hour or so
interesting, well it’s something to look into, but id like a place to communicate with like minded people.