Hacker News Reader

Comment by pentagrama | Hacker News Reader

Looks like a big pivot on target audience from developers to regular users, at least on the homepage https://ollama.com/ as a product. Before, it was all about the CLI versions of Ollama for devs, now it's not even mentioned. At the bottom of the blog post it says:

> For pure CLI versions of Ollama, standalone downloads are available on Ollama’s GitHub releases page.

Nothing against that, just an observation.

Previously I tested several local LLM apps, and the 2 best ones to me were LM Studio [1] and Msty [2]. Will check this one out for sure.

One missing feature that the ChatGPT desktop app has and I think is a good idea for these local LLM apps is a shortcut to open a new chat anytime (Alt + Space), with a reduced UI. It is great for quick questions.

[1] https://lmstudio.ai/

[2] https://msty.app/

View on HN

one of the maintainers for Ollama. I don't see it as a pivot. We are all developers ourselves, and we use it.

In fact, there are many self-made prototypes before this from different individuals. We were hooked, so we built it for ourselves.

Ollama is made for developers, and our focus in continually improving Ollama's capabilities.

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

You know that if you go to hugging face and find a gguf page, you can click on Deploy and select ollama. It comes with “run” but whatever—just change to pull. Has a jacked name, but works.

Also, if you search on ollama’s models, you’ll see user ones that you can download too

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 hopeful too -- where users can technically add models to Ollama directly. Although there is definitely some learning curve.

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

GLM 4.5 has a new/modified architecture. From what I understand, MLX was really one of the only frameworks that had support for it as of yesterday. LM Studio supports MLX as one backend. Everyone else was/is still developing support for it.

Ollama has the new 235B and 30B Qwen3 models from this week, so it’s not as if they have done nothing for a month.

ah, that explains why all the GLM quants are MLX models

just so you know, you can grab any gguf from huggingface and specify the quant like this:

  ollama pull hf.co/bartowski/nvidia_OpenCodeReasoning-Nemotron-7B-GGUF:IQ4_XS

qwen3 was updated less than a day ago: https://ollama.com/library/qwen3

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

You can do “tool calling” via Gemma3. The issue is that it all needs to be stuck in the user prompt as there’s no system prompt

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!

We can do function calling with Google's Gemma 3, just need to follow the right pattern.

All instruct templates are added in "post model training", and Gemma 3 works fine calling custom MCP tools using Jan and KoboldCpp.

I think welcoming another stream of users, in addition to develoeprs is a good idea.

Lots of people trying to being, and many with Ollama, and helping to create beginners is never a bad thing with tech.

I think welcoming another stream of users, in addition to develoeprs is a good idea.

Lots of people trying to being, and many with Ollama, and helping to create beginners is never a bad thing with tech.

Many things can be for both developers and end-users. Developers can use the API directly, end users, have more choices.

Are there any plans to improve observability toolset for developers? There is myriad of various AI chat apps, and there is no clear reason why another one from Ollama would be better. But Ollama is uniquely positioned to provide the best observability experience to its users because it owns the whole server stack, any other observability tool (eg Langfuse) may only treat it as a yet another API black box.

Does the new app make it easier for users to expose the Ollama daemon on the network (and mdns discovery )? It’s still trickier than needed for Home Assistant users to get started with Ollama (which tends to run on a different machine).

There's a simple toggle for juet that.

In the app settings now, there is a toggle for "Expose Ollama to the network" - it allows for other devices or services on the network to access Ollama.

I just updated and a bit annoying by default gemma3:4b was selected that I don't have on my local. I guess would be nicer to default to one of the models that are present.

It was nice it started downloading it but also there was no indication I don't have that model before hand until I opened drop-down to see download buttons.

But of course nice job guys.

Thanks for the kind words. Sorry about that, we are working out some of the initial experience for Ollama.

Big thanks to you and your team for this. My first time tying offline models, will the github cli use the same models by default (MacOS)?

The need to start a chat for a model that is not currently downloaded in order to initiate a download confused me for a minute the first time I tried it out. A more intuitive approach (which is the first thing I tried to do before I figured it out) might be to make the download icons in the model list clickable, to initiate a download. Then you could display a download progress bar in the list, and when models have been downloaded show a little "info" icon that is also clickable to display the model card, surface other model specific options, and enable deletion. Love the new UI, kudos!

Congratulations on launching the front-end, but I don't see how it can be made for developers and not have a Linux version.

Whoah, are you telling me that there are devs on Linux who use anything else than a tiled WM? CLI or GTFO /s

Its very strange, but they do have a Linux client that they refuse to mention in their blog post. I have no idea if this is a simple slip-up or if it was for some reason intentional.

https://ollama.com/download/linux

This link is for the existing cli version, not the new gui app.

I've never used a single linux GUI app in my 15 years of developing software. No company I've worked for even gives out linux laptops.

This caught me out yesterday. I was trying to move models onto external disk, and it seems to require re-installation? but there was no sign of the simple CLI option that was previously presented and I gave up.

As a developer feature request, it would be great if ollama could support more than one location at once, so that it is possible to keep a couple models 'live' but have the option to plug in an external disk with extra models being picked up auto-magically based on the ollama_models path please. Or maybe the server could present a simple html interface next to the API endpoint?

And just to say thanks for making these models easily accessible. I am agAInst AI generally, but it is nice to be able to have a play with these models locally. I havent found one that covers Zig, but appreciate the steady stream of new models to try. Thanks.

I just symbolically link the default model directory to a fast and cheap external drive. I agree that it would be nice to support multiple model directories.

Congratulations on the next release.

I really like using ollama as a backend to OpenWebUI.

I don't have any windows machines and I don't work primarily on macos, but I understand that's where all the paying developers are, in theory.

Did y'all consider a partnership with one of the existing UI and bundle that, similar to duckdb approach?

I’m just curious because I don’t use Ollama and have some spare vram: How do you use it and what models do you use?

How about include MCP option?

Thanks for including it. Ollama is very good at what it does. Including the feature is showing mindful growth in helping ollama be that skateboard, scooter, car, etc that the developer needs for LLM at that time. Making it appeal to casual/hobbyist is the right approach.

PS totally running windows here and using kesor/ollama-proxy if I need to make it externally available.

While you are here: what's the state of external contributing for the project? I see literally hundreds of open PRs, and it's a bit discouraging, tbh.

I think having a bash script as the linux installation is more of a stop-gap measure than truly supporting Linux. And ollama is FOSS compared to LM Studio and Msty (as someone who switched from ollama to LM Studio; I'm very happy to see the frontend development of ollama and an easier method of increasing the context length of a model).

lol the Ollama app is closed source

Oof well there goes my desire to switch back.

this is actually positive even for devs. The more users have ollama installed then you can release some desktop ai app for them and don't have to bundle additional models in your own app. Easier to provide to such user free or cheaper subscription because you don't have additional costs. Latest Qwen30B models area really powerful.

Would be even better if there was a installation template that checks if Ollama is installed and if not download it as sub installation first checking user computer specs if enough RAM and fast enough CPU/GPU. Also API to prompt user (ask for permission) to install specific model if haven't been installed.

> Would be even better if there was a installation template that checks if Ollama is installed and if not download it as sub installation first..... Also API to prompt user (ask for permission) to install specific model if haven't been installed.

That's actually what we've done for our own App [1]. It checks if Ollama and other dependencies are installed. No model is bundled with it. We prompt user to install a model (you pick a model, click a button and we download the model; similar if you wish to remove a model). The aim is to make it quite simple for non-technical folks to use.

1) https://ai.nocommandline.com/

Have you seen https://pygpt.net/ ? Overloaded interface and little unfortunate name aside, this seems to be the best one I tried.

> little unfortunate name aside

What's wrong with the name? Are you referring to the GPT trademark? That was rejected.

I may be too picky, and on reflection I probably shouldn't be - it was just my first thought when I saw what the project actually is for the first time.

What I meant is the "Py" prefix is typically used for Python APIs/libraries, or Python bindings to libraries in other languages. Sometimes as a prefix for dev tool names like PyInstaller or PyEnv. It's just less often used for standalone apps, only to indicate the project was developed in Python.

> One missing feature that the ChatGPT desktop app has and I think is a good idea for these local LLM apps is a shortcut to open a new chat anytime (Alt + Space), with a reduced UI. It is great for quick questions.

This is exactly what I've implemented for my Qt C++ app: https://www.get-vox.com

I’d heard of Msty and briefly tried it before. I checked the website again and it looks quite feature rich. I hadn’t known about LM Studio, and I see that it allows commercial use for free (which Matt doesn’t).

How would you compare and contrast between the two? My main use would be to use it as a tool with a chat interface rather than developing applications that talk to models.

I use Msty all the time and I love it. It just works and it's got all features I want now, including generating alternate responses, swapping models mid-chat, editing both sent messages and responses, ...

I also tried LM Studio a few months back. The interface felt overly complex and I got weird error messages which made it look like I'd have to manually fix errors in the underlying python environment. Would have been fine if it was for work, but I just wanted to play around with LLMs in my spare time so I couldn't be bothered.

LM studio just changed their terms to allow commercial usage for free and without any restrictions or additional actions required.

I've used Msty but it seems like LM studio is moving faster, which is kind of important in this space. For example Msty still doesn't support MCP

This makes me really wonder about the relationship between Open WebUI & Ollama

Is there a way to get LM Studio to talk to remote OpenAI API servers and cloud providers?

LM Studio is for hosting/serving local LLMs. Its chat UI is secondary and is pretty limited.

Good to know, thanks. What do people generally use to connect to it for chat?

Msty (msty.app). Currently they're working on Msty Studio which is only accessible to people with a license, but the desktop app is pretty good, it just doesn't have tool (MCP) support.

Doesn't Msty alreayd run models? What is LM Studio needed for in this setup?

OpenWebUI seems to be the standard. Easy to spin it up in a docker container pointed to 127.0.0.1:1234/v1 and away you go.

If you have a Mac, I recommend https://boltai.com/ for that

That feature is available in HugstonOne with a new tab, among other features :) Edit: Is incredible how unethical are all the other developers with their crappie spam unrelated. Ollama is a great app and pioneer of AI, cudos and my best thanks.

Reply on news.ycombinator.com