I’ve just re-discovered ollama and it’s come on a long way and has reduced the very difficult task of locally hosting your own LLM (and getting it running on a GPU) to simply installing a deb! It also works for Windows and Mac, so can help everyone.
I’d like to see Lemmy become useful for specific technical sub branches instead of trying to find the best existing community which can be subjective making information difficult to find, so I created !Ollama@lemmy.world for everyone to discuss, ask questions, and help each other out with ollama!
So, please, join, subscribe and feel free to post, ask questions, post tips / projects, and help out where you can!
Thanks!
TBH you should fold this into localllama? Or open source AI?
I have very mixed (mostly bad) feelings on ollama. In a nutshell, they’re kinda Twitter attention grabbers that give zero credit/contribution to the underlying framework (llama.cpp). And that’s just the tip of the iceberg, they’ve made lots of controversial moves, and it seems like they’re headed for commercial enshittification.
They’re… slimy.
They like to pretend they’re the only way to run local LLMs and blot out any other discussion, which is why I feel kinda bad about a dedicated ollama community.
It’s also a highly suboptimal way for most people to run LLMs, especially if you’re willing to tweak.
I would always recommend Kobold.cpp, tabbyAPI, ik_llama.cpp, Aphrodite, LM Studio, the llama.cpp server, sglang, the AMD lemonade server, any number of backends over them. Literally anything but ollama.
…TL;DR I don’t the the idea of focusing on ollama at the expense of other backends. Running LLMs locally should be the community, not ollama specifically.
Thanks for Lemonade hint. For Ryzen AI: https://github.com/lemonade-sdk/lemonade (linux=cpu for now)
You can still use the IGP, which might be faster in some cases.
Indeed, Ollama is going a shady route. https://github.com/ggml-org/llama.cpp/pull/11016#issuecomment-2599740463
I started playing with Ramalama (the name is a mouthful) and it works great. There is one or two more steps in the setup but I’ve achieved great performance and the project is making good use of standards (OCI, jinja, unmodified llama.cpp, from what I understand).
Go and check it out, they are compatible with models from HF and Ollama too.
What would you recommend to hook to my home assistant?
Totally depends on your hardware, and what you tend to ask it. What are you running? What do you use it for? Do you prefer speed over accuracy?
My HomeAssistant is running on Unraid but I have an old NVIDIA Quadro P5000. I really want to run a vision model so that it can describe who is at my doorbell.
Oh actually that’s a great card for LLM serving!
Use the llama.cpp server from source, it has better support for Pascal cards than anything else:
https://github.com/ggml-org/llama.cpp/blob/master/docs/multimodal.md
Gemma 3 is a hair too big (like 17-18GB), so I’d start with InternVL 14B Q5K XL: https://huggingface.co/unsloth/InternVL3-14B-Instruct-GGUF
Or Mixtral 24B IQ4_XS for more ‘text’ intelligence than vision: https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF
I’m a bit ‘behind’ on the vision model scene, so I can look around more if they don’t feel sufficient, or walk you through setting up the llama.cpp server. Basically it provides an endpoint which you can hit with the same API as ChatGPT.
I’m going to go out on a limb and say they probably just want a comparable solution to Ollama.
OK.
Then LM Studio. With Qwen3 30B IQ4_XS, low temperature MinP sampling.
That’s what I’m trying to say though, there is no one click solution, that’s kind of a lie. LLMs work a bajillion times better with just a little personal configuration. They are not magic boxes, they are specialized tools.
Random example: on a Mac? Grab an MLX distillation, it’ll be way faster and better.
Nvidia gaming PC? TabbyAPI with an exl3. Small GPU laptop? ik_llama.cpp APU? Lemonade. Raspberry Pi? That’s important to know!
What do you ask it to do? Set timers? Look at pictures? Cooking recipes? Search the web? Look at documents? Do you need stuff faster or accurate?
This is one reason why ollama is so suboptimal, with the other being just bad defaults (Q4_0 quants, 2048 context, no imatrix or anything outside GGUF, bad sampling last I checked, chat template errors, bugs with certain models, I can go on). A lot of people just try “ollama run” I guess, then assume local LLMs are bad when it doesn’t work right.
I have a MacBook 2 pro (Apple silicon) and would kind of like to replace Google’s Gemini as my go-to LLM. I think I’d like to run something like Mistral, probably. Currently I do have Ollama and some version of Mistral running, but I almost never used it as it’s on my laptop, not my phone.
I’m not big on LLMs and if I can find an LLM that I run locally and helps me get off of using Google Search and Gimini, that could be awesome. Currently I use a combo of Firefox, Qwant, Google Search, and Gemini for my daily needs. I’m not big into the direction Firefox is headed, I’ve heard there are arguments against Qwant, and using Gemini feels like the wrong answer for my beliefs and opinions.
I’m looking for something better without too much time being sunk into something I may only sort of like. Tall order, I know, but I figured I’d give you as much info as I can.
Actually, to go ahead and answer, the “fastest” path would be LM Studio (which supports MLX quants natively and is not time intensive to install), and a DWQ quantization (which is a newer, higher quality variant of MLX models).
Hopefully one of these models, depending on how much RAM you have:
https://huggingface.co/mlx-community/Qwen3-14B-4bit-DWQ-053125
https://huggingface.co/mlx-community/Magistral-Small-2506-4bit-DWQ
https://huggingface.co/mlx-community/Qwen3-30B-A3B-4bit-DWQ-0508
https://huggingface.co/mlx-community/GLM-4-32B-0414-4bit-DWQ
With a bit more time invested, you could try to set up Open Web UI as an alterantive interface (which has its own built in web search like Gemini): https://openwebui.com/
And then use LM Studio (or some other MLX backend, or even free online API models) as the ‘engine’
Alternatively, especially if you have a small RAM pool, Gemma 12B QAT Q4_0 is quite good, and you can run it with LM Studio or anything else that supports a GGUF. Not sure about 12B-ish thinking models off the top of my head, I’d have to look around.
This is all new to me, so I’ll have to do a bit of homework on this. Thanks for the detailed and linked reply!
I was a bit mistaken, these are the models you should consider:
https://huggingface.co/mlx-community/Qwen3-4B-4bit-DWQ
https://huggingface.co/AnteriorAI/gemma-3-4b-it-qat-q4_0-gguf
https://huggingface.co/unsloth/Jan-nano-GGUF (specifically the UD-Q4 or UD-Q5 file)
they are state-of-the-art at this size, as far as I know.
Awesome, I’ll give these a spin and see how it goes. Much appreciated!
Honestly perplexity, the online service, is pretty good.
As for local running, one question first: how much RAM does your Mac have? This is basically the factor for what model you can and should run.
8GB
8GB?
You might be able to run Qwen3 4B: https://huggingface.co/mlx-community/Qwen3-4B-4bit-DWQ/tree/main
But honestly you don’t have enough RAM to spare, and even a small model might bog things down. I’d run Open Web UI or LM Studio with a free LLM API, like Gemini Flash, or pay a few bucks for something off openrouter. Or maybe Cerebras API.
…Unfortunely, LLMs are very RAM intensive, and >4GB (more realistically like 2GB) is not going to be a good experience :(
Good to know. I’d hate to buy a new machine strictly for running an LLM. Could be an excuse to pickup something like a Framework 16, but realistically, I don’t see myself doing that. I think you might be right about using something like Open Web UI or LM Studio.
Perhaps give Ramalama a try?
Instance independent link: !Ollama@lemmy.world
Share links to communities this way, so everyone can subscribe easily.
You should also post about this in !newcommunities@lemmy.world and !communitypromo@lemmy.ca for better discoverability!
Thanks will do all that!
Cool! I’ll subscribe. I’ve got about a dozen projects I’d like to build with Ollama, if I’ll get the motivation and free time who knows?
Start now! Install it, get a python environment up and running if you haven’t already, and get that first play-around project working which you work outwards from!
Already setup! I think the first thing I want to do is setup retrieval augmented generation. Several of my hobby ideas will require it I think. Started trying to read up on it a couple days ago and I had a serious lack of focus going on.
I’ve been kind of hoping to come across a super simple way to implement it, but haven’t exactly looked much yet.
Sounds like a great first question! Go for it!
There is also !localllama@sh.itjust.works :)
crossposting between the communities can help grow both
