I am embarrassed to say that I was not aware that ollama was NOT* open source and running on an MIT license I will definitely check this out later. Hopefully more open source des take interest in supporting an open source AI ecosystem.
Ollama is not open source? It seems to be MIT licensed: https://github.com/ollama/ollama/blob/main/LICENSE. Am I overlooking something?
My mistake it I swaped MIT license with AGPL. I was under the impression that an MIT license was less permissive than an AGPL one.
Just to know if you are not aware, you are putting a penny in a hot debate in the free software community on which license is the more open, is the best.
The MIT is clearly the most permissive because it allows you, among other things, to just run with the software and close it, adding your modification and sell it without sharing source.
Afero GPL prevents you from selling the software or even selling services that run the software without sharing/publishing it.
In a MIT->AGPL swap you will find people who consider it a step into being closer to free software ideals and people who consider it getting further away from it.
Why not use lamma.cpp and opencode?
Genuinely asking, what is the advantage of ollama, a nice ui for loading models?
Until now, ollama model router implementation is still better. There is still no model queue system in llama-server.
llama-server is also released around last year only.
Maybe after https://github.com/ggml-org/llama.cpp/issues/21678#issuecomment-4592982609 then there is not much reason to use ollama.
Anyway i stopped using ollama and just deal with the issue now. Because most huggingface models work better with llama.cpp.
But i dont understand why everyone just keep bashing ollama. Does no one run multiple models?
