

Yay more people to join Pixelfed!


Yay more people to join Pixelfed!
Sounded like a cool idea at the time, at least they tried something new!
Ollama with gemma 4 for LLM stuff, coding brainstorming, etc.
Comfy ui with z-image or stable diffusion for images.
For really lightweight models, Qwen3:8b is pretty good for an 8gb graphics card.
Gemma 4:e4b is pretty good too. I usually sun that on my 16gb gpu.
Obviously the little ones aren’t as good as big ones, but you can always rely on real intelligence to fill in the gaps


$2 per year for my domain name.


I will say, I do like the idea of physically disabled folks getting to drive or co trolls robots/remote cars, especially if they have microphones and stuff.
I’ll look for the video, but there was this really cool Cafe in Japan that employed bed-ridden people to work as robots in a cafe
Yeah I was curious about that. Like I can poke around in the immich directory, but the actual pictures are stored in a weird structure. Do you have any recommendations?
One of my first self hosting projects was a jellyfin server. Double check, but I think the main hardware requirements are just 4GB of RAM and enough harddrive space for your videos/files!
I really like immich too. It’s like Google photos, but self hosted. It’s super fast for uploading and backing up your photos over your local network. Immich also needs at least 4GB of RAM I think


I guess I have been using gemma4 fro more role playing games. Qwen3.5 seems to be better coder actually


I also recommend gemma4 or qwen3.5. Both super solid in my experience for how lightweight they are


I don’t think VR need to be the “next big thing” but it is just a fun little thing. I have an old HTC Vive and I love firing up beat saber and taking turns with folks when I have company over.
Also vr chat is great!
It seem like people are obsessed with making vr better amd more widespread. I’m content with it to just be a fun little thing I break out every once in a while
Too late, I’m already in love with linux mint!
Yeah I too am a big supporter. There are already all sorts of open models on Hugging Face. The smaller fined tuned models are often better than the big models at the specific tasks they are trained for.
There’s just a big learning curve at how to start using the open weight models and LoRAs on Hugging Face for example