77
Over Synology, and looking to build my first home lab. Could use some advice on parts...
(pcpartpicker.com)
this post was submitted on 23 May 2025
77 points (97.5% liked)
Selfhosted
59850 readers
313 users here now
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.
-
Posts here are to be centered around self-hosting. Please ensure it is clear in your post how it relates to self-hosting.
-
Don't duplicate the full text of your blog or git here. Just post the link for folks to click.
-
Submission headline should match the article title.
-
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!
founded 3 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Dedicated GPUs are obviously going to be more powerful. I've never run ai before so maybe someone else can weigh in on the requirements for it, but I can say for sure that an igpu is good enough for jellyfin transcoding. It also depends on your budget, do you want to spend the extra money just for a dedicated GPU?
If you go igpu route I think that Intel is recommended over AMD, but you should probably do extra research on that before buying
My amd igpu works just fine for jellyfin. LLMs are a little slow, but that's to be expected.
Yeah, I'm not sure if I really want to deal with an llm. It would mostly be for home assistant, so nothing too crazy.
I have a very similar NAS I built. The Home Assistant usage doesn't really even move the needle. I'm running around 50 docker containers and chilling at about 10% cpu.
The LLM for home assistant, or just HA in general doesn't move the needle? My HA is also pretty low key, but I was considering the idea of running my own small llm to use with HA to get off of OpenAI. My current AI usage is very small, so I wouldn't need too much on the GPU side I'd imagine, but I don't know what's sufficient.
Just home assistant doesn't move the needle. The llms hit the igpu hard and my cpu usage spikes to 70-80% when one is thinking.
But my llms i'm running are ollama and invokeai each with several different models just for fun.