Selfhosted
A place to share alternatives to popular online services that can be self-hosted without giving up privacy or locking you into a service you don't control.
Rules:
-
Be civil: we're here to support and learn from one another. Insults won't be tolerated. Flame wars are frowned upon.
-
No spam posting.
-
Posts have to be centered around self-hosting. There are other communities for discussing hardware or home computing. If it's not obvious why your post topic revolves around selfhosting, please include details to make it clear.
-
Don't duplicate the full text of your blog or github here. Just post the link for folks to click.
-
Submission headline should match the article title (don’t cherry-pick information from the title to fit your agenda).
-
No trolling.
Resources:
- selfh.st Newsletter and index of selfhosted software and apps
- awesome-selfhosted software
- awesome-sysadmin resources
- Self-Hosted Podcast from Jupiter Broadcasting
Any issues on the community? Report it using the report flag.
Questions? DM the mods!
view the rest of the comments
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 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.
Yeah, just paying for LLM APIs is dirt cheap, and they (supposedly) don't scrape data. Again I'd recommend Openrouter and Cerebras! And you get your pick of models to try from them.
Even a framework 16 is not good for LLMs TBH. The Framework desktop is (as it uses a special AMD chip), but it's very expensive. Honestly the whole hardware market is so screwed up, hence most 'local LLM enthusiasts' buy a used RTX 3090 and stick them in desktops or servers, as no one wants to produce something affordable apparently :/
@brucethemoose @WhirlpoolBrewer
*1650 and it works like a charm 🤌🏾
You mean GPU? Yeah, it's good, I was strictly talking about purchasing a laptop for LLM usage, as most are less than ideal for the money. Laptop vram pools are relatively small and SO-DIMMS are usually very slow.
Things will get much better once the "Max" AMD SKUs proliferate.
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.