MASSIVE llama cpp now now ships with a built-in web UI stop using ollama, there are no more excuses

Ollama has pretty much been standardized as local API provider Stop hating ollama, they brought good UX to the market

When you install ollama, it just works, utilizes gpu out of the gate. Llama-cpp on the other hand, I have to memorize a list of arcane console incantations that build wheels with cmake, etc., and after a few bluescreens and version mismatches later, it finally worked. Painful

Been testing it in preview for a while. It's quite solid.

It looks minimalistic yet powerful. I am a fan.

Why should we stop using ollama?

Solid article for those interested

why so much hate for ollama though?

stop calling me out like this

nice demo, multithreading without streaming interruption convinces me to try. Thanks!

to top it off, that’s a really pretty UI

It has for literally years, but still, all promotion for it is good I guess

what's wrong with ollama?

Ollama comes with an UI as well

my excuse is I have 8gb of ram

I thought it always had one? been using that when running local

It was in preview, finally stable

But I like @lmstudio

Must we always use a cloned interface from ChatGPT or can we ever move past it? Not being critical because this actually looks really good and I'm excited.

llama.cpp >> ollama fr fr

Awesome

Thanks

does llama cpp have better performance optimizations than ollama? esp for apple silicon?

That’s fine but does llama.cpp support OpenAI-compatibility API like Ollama?

Thanks for sharing, thats really interesting.

Wow that is nice

Ahmad, you're right, the built-in UI is a game-changer! It's about time we move on from Ollama, no?

It's always had a Web UI

why are you asking an LLM to do a 1st grader's homework...

Built-in web UI? Game changer. No more terminal commands for normies. llama.cpp is making local AI ridiculously accessible 🚀

@grok explain what is llama cpp and how it related to ollama

@grok major differences?

A built-in web UI? That’s a game changer. Finally, no more wrestling with those command lines!

that's pretty convenient

but what's the difference? they both look the same

Why is this grounds to stop using ollama ?