Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ollama's new app

ollama.com

Post reply on HN
Print view View original

161–170 of 299 posts

Re: Ollama's new app

#161

Post by kergonath »

jart wrote: post #133
Petersipoi wrote: post #127

Earlier quoted context omitted.

There is a big difference between fun exercise and actually creating something that competes with the apps you can download. Building something on par with Claude Desktop, ChatGPT Desktop, etc. would be a lot of work. And I don't think the payoff would be there for most people.

Most people aren't hackers. Thanks to LLMs and vibe coding, even they can now take a can-do attitude to life that feels empowering. There's no longer any excuse to languish in helpless misery and negativity. You can just build things.

I have other things to do with my day than vibe-coding yet another stupid chat app with fewer features than one I can just download and get running in minutes. It’s not helplessness or misery, it’s just the finite number of hours I have in a day and the fact that other things are more interesting than that. I don’t grow my own wheat or maintain my own OS, either.

Re: Ollama's new app

#162

Post by kinduff »

mchiang wrote: post #143
pmarreck wrote: post #103

Earlier quoted context omitted.

do you know why ollama hasn't updated its models in over a month while many fantastic models have been released in that time, most recently GLM 4.5? It's forcing me to use LM Studio which I for whatever reason absolutely do not prefer. thank you guys for all your work on it, regardless

We work closely with majority of research labs / model creates directly. Most of the times we will support models on release day. There are sometimes where the release window for major models are fairly close - and we just have to elect to support models where we believe will better support a majority of users. Nothing out of spite, and purely limited by the amount of effort required to support these models. We are h…

Would love to add models direclty. And don't worry, we will figure it out!

Re: Ollama's new app

#163

Post by mchiang »

whs wrote: post #142
nileshtrivedi wrote: post #126

Earlier quoted context omitted.

Question since you are here, how long before tool-calling is enabled for Gemma3 models?

Seems that Google intend it to be that way - https://ai.google.dev/gemma/docs/capabilities/function-calli... . I suppose they are saying that the model is good enough that if you put the tool call format in prompt it should be able to handle any formats. I use PetrosStav/gemma3-tools and it seems that it only works half of the time - the rest the model call the tool but it doesn't get properly parsed by Ollama.

unfortunately, I don't think gemma 3 supports tool calling well. It's not trained into the model, and the 'support' for tool calling is post model training.

We are working with Google, and trying to give the feedback on improving tool calling capabilities for future Gemma models. Fingers crossed!

Re: Ollama's new app

#164

Post by Eisenstein »

kid64 wrote: post #141
halJordan wrote: post #114

Earlier quoted context omitted.

The dev is very opinionated

Does https://github.com/open-webui/mcpo/ not fill this gap?

That is the initially mentioned MCP to OpenAPI proxy.

EDIT: To add a bit, MCP is more than just tools, which is the only use case MCPO supports.

Re: Ollama's new app

#165

Post by grumbelbart2 »

hodgehog11 wrote: post #149

Not surprising; Ollama is set on becoming the standard interface for companies to deploy "open" models. The focus on "local" is incidental, and likely not long term. I'm sure Ollama is going to announce a plan to use "open" models through their own cloud-based API using this app.

> The focus on "local" is incidental

Strongly disagree with this. It is the default go-to for companies that cannot use cloud-based services for IP or regulatory reasons (think of defense contractors). Isn't that the main reason to use "open" models, which are still weaker than closed ones?

Re: Ollama's new app

#167

Post by otabdeveloper4 »

throwawaylaptop wrote: post #101

I must be stupid because I don't understand how this is different than having several tabs open in a browser with all the AI services I'd like open?

Repackaging other people's work while adding literally nothing useful is Ollama's entire gig.

This hype bubble is as disgusting and scummy as the previous one.

Re: Ollama's new app

#168

Post by hyperbolablabla »

jart wrote: post #136
coder543 wrote: post #95

I am somewhat surprised that this app doesn't seem to offer any way to connect to a remote Ollama instance. The most powerful computer I own isn't necessarily the one I'm running the GUI on.

This. This. A thousand times this. I hate Windows / MacOS but love their desktops. I love Linux / BSD but hate their desktops. So my most expensive most powerful workstation is always a headless Linux machine that I ssh into from a Windows or MacOS toy computer. Unfortunately most developers do not understand this. Every time I run a command in the terminal and it tries to open a browser tab without printing the URL,…

Hey Justine! Thank you for all your fantastic work

Re: Ollama's new app

#170

Post by polotics »

Eisenstein wrote: post #96
mchiang wrote: post #61

Earlier quoted context omitted.

Choice is good but here is why prefer Ollama over others (I'm biased because I work on Ollama). Supporting multiple backends is HARD. Originally, we thought we'd just add multiple backends to Ollama - MLX, ROCm, TRT-LLM, etc. It sounds really good on paper. In practice, you get into the lowest common denominator effect. What happens when you want to release Model A together with the model creator, and backend B doesn…

Sure, those are all difficult problems. Problems that single devs are dealing with every day and figuring out. Why is it so hard for Ollama? What seems to be true is that Ollama wants to be a solution that drives the narrative and wants to choose for its users rather than with them. It uses a proprietary model library, it built itself on llama.cpp and didn't upstream its changes, it converted the standard gguf model…

Started with ollama, am at the stage of trying llama.ccp and realising there RPC just works, and ollama's promises of distributed runs is just hanging in the air, so indeed the convenience of ollama is starting to lose its appeal.

So, questions: what are the changes that they didn't upstream, is this listed somewhere? what is the impact? are they also changes in ggml? what was the point of the gguf format change?

Post reply on HN