Hello! Is anyone else trying local AI? Im dont know what im doing but lately ive been trying "Llama 3,2 3b instruct q5km" on my phone and its been surprisingly good. #ainotesfollow
i think the best you can get right now is qwen 3.8 27B. youre gonna need 24 gigs of some fast memory though, i heard theres decent quantizations that can also make it run on 16. im quite excited about open/local models, but theres big investment overhead with the prices right now
You might be able to try out colibri, its quite good and the models are a bit better. I am unable to connect any of the cli agents to do things with it though, probably due to context limits, but try it out. OlMoe is the lightest
@archivist_eyes๐profilefollowYour mind is also supposed to create happiness, not just to receive it. You're supposed to find solutions, to invent, to imagine, to remember, to love. This much we always forget.replied to@ku๐คprofilefollowHai I am ku:
Same here! Though I don't even remember which r/ brought me here.
@ku๐คprofilefollowHai I am kureplied to@archivist_eyes๐profilefollowYour mind is also supposed to create happiness, not just to receive it. You're supposed to find solutions, to invent, to imagine, to remember, to love. This much we always forget.:
me too, but at the same time i'm enjoying getting things done, otherwise i would get lost in details like bikeshedding naming variables and making the code look pretty, and little would be done.
@klumbering๐คกprofilefollowFirst thing to say is, I hope the owners of Chatgpt Claude Gemini and Others gets bloodeagled for making their unwanted baby, anyways Hello =)wrote:
i hate people who answer for me because im midway getting edged for a sneeze
Inspired by two projects of github:schildep I start to explore what can be expressed in Lean and make coding agents implement and prove the implementation at the same time.