Ollama: All Aboard Open Models
ollama.com
Ollama: All Aboard Open Models
1–10 of 60 posts
Re: Ollama: All Aboard Open Models
#2Will Ollama finally properly credit llama.cpp ? Or will they continue to rebrand new llama.cpp features as their own?
Re: Ollama: All Aboard Open Models
#3>Today, we’re announcing that Ollama has raised money from VCs...
Note to self, Enshittification ahead. Don't use any ollama services unless it's calling an industry standard api.
Re: Ollama: All Aboard Open Models
#4To any ollama.com dudes and dudettes reading this: why won't you offer any embedding models on your subscription when they are readily supported by the software and fairly efficient to run?
Re: Ollama: All Aboard Open Models
#5This is all lovely and I wish them the best.
But please don't use ollama, or their quants. Not only is the app itself slower than pure llamacpp. But their quants are often no where near the best.
I really hope people start with something like unsloth, as their software and quants are really much better all around.
Re: Ollama: All Aboard Open Models
#6- stop using ollama
Re: Ollama: All Aboard Open Models
#7- stop using ollama - https://sleepingrobots.com/dreams/stop-using-ollama/
I wasn't aware of the politics behind Ollama but I have noticed the lack of variety in quant versions, the lag between availability on Ollama, and their push to get you to use their cloud versions.
I'm going to uninstall Ollama.
Re: Ollama: All Aboard Open Models
#8This is all lovely and I wish them the best. But please don't use ollama, or their quants. Not only is the app itself slower than pure llamacpp. But their quants are often no where near the best. I really hope people start with something like unsloth, as their software and quants are really much better all around.
For anyone who may not be aware it exists: https://unsloth.ai/docs/new/studio
Re: Ollama: All Aboard Open Models
#9https://github.com/ollama/ollama/issues/11772
A year and still no implementation for such a basic need as offloading MoE layers onto the CPU selectively. On llama.cpp I can get models like Qwen 35BA3B running partially on gpu/cpu with 40t/s on a laptop thanks to --n-cpu-moe but on this VC funded joke it would be simply unusable. I can't quite understand how you make a wrapper so much worse than the code you're ripping out.
>This funding is fuel for what’s ahead. Ollama sits front and center in the open model ecosystem
No.
Re: Ollama: All Aboard Open Models
#10- stop using ollama - https://sleepingrobots.com/dreams/stop-using-ollama/
I don't use local models often enough, but this convinced me to uninstall ollama. Now I need to figure out which of the options at the end of that post is the best alternative for me.