Pro to Technology@lemmy.worldEnglish • 5 days agoGoogle quietly released an app that lets you download and run AI models locallygithub.comexternal-linkmessage-square41fedilinkarrow-up1240arrow-down10
arrow-up1240arrow-down1external-linkGoogle quietly released an app that lets you download and run AI models locallygithub.comPro to Technology@lemmy.worldEnglish • 5 days agomessage-square41fedilink
minus-squareAmbiguousPropslinkfedilinkEnglish23•5 days agoThat’s fair, but I think I’d rather self host an Ollama server and connect to it with an Android client in that case. Much better performance.
minus-square@OhVenus_Baby@lemmy.mllinkfedilinkEnglish2•4 days agoHow is Ollama compared to GPT models? I used the paid tier for work and I’m curious how this stacks up.
minus-squareAmbiguousPropslinkfedilinkEnglish1•4 days agoIt’s decent, with the deepseek model anyway. It’s not as fast and has a lower parameter count though. You might just need to try it and see if it fits your needs or not.
minus-squareGreg ClarkelinkfedilinkEnglish4•5 days agoYes, that’s my setup. But this will be useful for cases where internet connection is not reliable
minus-squareGreg ClarkelinkfedilinkEnglish3•5 days agoHas this actually been done? If so, I assume it would only be able to use the CPU
minus-square@Euphoma@lemmy.mllinkfedilinkEnglish7•4 days agoYeah I have it in termux. Ollama is in the package repos for termux. The speed it generates does feel like cpu speed but idk
minus-squareDiplomjodlerlinkfedilinkEnglish3•4 days agoIs there any useful model you can run on a phone?
minus-square@gens@programming.devlinkfedilinkEnglish2•4 days agoLlama.cpp (on which ollama runs on) can. And many chat programs for phones can use it.
Ollama can’t run on Android
That’s fair, but I think I’d rather self host an Ollama server and connect to it with an Android client in that case. Much better performance.
How is Ollama compared to GPT models? I used the paid tier for work and I’m curious how this stacks up.
It’s decent, with the deepseek model anyway. It’s not as fast and has a lower parameter count though. You might just need to try it and see if it fits your needs or not.
Yes, that’s my setup. But this will be useful for cases where internet connection is not reliable
You can use it in termux
Has this actually been done? If so, I assume it would only be able to use the CPU
Yeah I have it in termux. Ollama is in the package repos for termux. The speed it generates does feel like cpu speed but idk
Is there any useful model you can run on a phone?
Llama.cpp (on which ollama runs on) can. And many chat programs for phones can use it.
Try PocketPal instead