Ollama's new app • Hacker News Board

Re: Ollama's new app

#91

Post by accrual » Thu, Jul 31, 2025, 1:57 AM UTC

I gave the Ollama UI a try on Windows after using the CLI service for a while.

- I like the simplicity. This would be perfect for setting up a non-technical friend or family member with a local LLM with just a couple clicks

- Multimodal and Markdown support works as expected

- The model dropdown shows both your local models and other popular models available in the registry

I could see using this over Open WebUI for basic use cases where one doesn't need to dial in the prompt or advanced parameters. Maybe those will be exposed later. But for now - I feel the simplicity is a strength.

Re: Ollama's new app

#92

Post by SamPatt » Thu, Jul 31, 2025, 2:04 AM UTC

No Linux, that's a bummer. I've been using it in Linux for inference for ages, it's pretty easy to use.

I'll stick with OpenWebUI then.

Re: Ollama's new app

#93

Post by Eisenstein » Thu, Jul 31, 2025, 2:05 AM UTC

jonahbenton wrote: post #56

apitman wrote: post #38

I've been on something of a quest to find a really good chat interface for LLMs. Most import feature for me is that I want to be able to chat with local models, remote models on my other machines, and cloud models (OpenAI API compatible). Anything that makes it easier to switch between models or query them simultaneously is important. Here's what I've learned so far: * Msty - my current favorite. Can do true simultan…

OpenWebUI is what you are looking for from a usability perspective. Supports many models chat.

OpenWebUI refuses to support MCP and uses an MCP to OpenAPI proxy which often doesn't work. If you don't like or need MCP, then it is a good choice.

Re: Ollama's new app

#94

Post by nguyenkien » Thu, Jul 31, 2025, 2:06 AM UTC

delduca wrote: post #29

Native or another electron crap?

It's use system webview.

Re: Ollama's new app

#95

Post by coder543 » Thu, Jul 31, 2025, 2:11 AM UTC

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.

Re: Ollama's new app

#96

Post by Eisenstein » Thu, Jul 31, 2025, 2:11 AM UTC

mchiang wrote: post #61

uyzstvqs wrote: post #37

There's also Jan AI, which supports Linux, MCP, any Vulkan GPU, any Llama.cpp-compatible model, and optionally multiple cloud models as well. That seems like a better solution than this.

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 weights into some unusable file type that only worked with itself, etc.

Sorry but I don't buy it. These are not intractable problems to deal with. These are excuses by former docker creators looking to destroy another ecosystem by attempting to coopt it for their own gain.

Re: Ollama's new app

#97

Post by thorum » Thu, Jul 31, 2025, 2:13 AM UTC

If you’re a power user of these LLMs and have coding experience, I actually recommend just whipping together your own bespoke chat UI that you can customize however you like. Grab any OpenAI compatible endpoint for inference and a frontend component framework (many of which have added standard Chat components) - the rest is almost trivial. I threw one together in a week with Gemini’s assistance and now I use it every day. Is it production ready? Hell no but it works exactly how I want it to and whenever I find myself saying “I wish it could do XYZ…” I just add it.

Re: Ollama's new app

#98

Post by dcreater » Thu, Jul 31, 2025, 2:15 AM UTC

swyx wrote: post #7

finally, what took so long lmao if im being honest i care more about multiple local ai apps on my desktop all hooking into the same ollama instance rather than all downloading their own models as part of the app so i have like multiple 10s of gbs of repeated weights all over the place because apps dont talk to each other what does it take for THAT to finally happen

And this move by Ollama is going exactly in the wrong direction.

Its finally the push I need to move away. I predict ollama will only get worse from here on.

Re: Ollama's new app

#99

Post by SchemaLoad » Thu, Jul 31, 2025, 2:19 AM UTC

amelius wrote: post #8

rihegher wrote: post #2

"Ollama’s new app is now available for macOS and Windows" linux sounds out for now

Shouldn't the LLM be able to code the linux version?

Never ask an AI hype bro why after years of coding agents and 10x productivity, software is just as shit as it always has been.

Re: Ollama's new app

#100

Post by danielcorin » Thu, Jul 31, 2025, 2:19 AM UTC

I’ve been building a Swift app [1], compatible with OpenAI APIs, easy model switching across providers, and with hotkeys for OS integration to capture text and images. It’s far more minimal than most other LLM frontends I’ve tried, but it’s been sticky for me.

[1]: https://www.wvlen.llc/apps/tomo