I don’t know if the GUID Partition Table fuckery is better or worse than what I was originally expecting when I thought your title meant you’d replaced your filesystem with ChatGPT and just let it hallucinate files in and out of existence for you. 🫠️

I ran a 3x3 grid configuration for a long time as well – until I finally realized I needed more than that and upgraded to a 5x3 grid! 😅️

I use the center desktop for a maximized browser window and the most important stuff is usually in a plus shape immediately adjacent to that with less important things further away.

Kiki and Bouba

If you just pulled the default version of qwen3.5 from ollama’s repo you downloaded a mediocre one that only uses ~6GB.

Check ollama show qwen3.5 and see if you get something like this in the result:

  Model
    architecture        qwen35    
    parameters          9.7B      
    context length      262144    
    embedding length    4096      
    quantization        Q4_K_M 

This is the default version I got when I first tried using ollama without any experience. It worked, but it’s a heavily quantized, lower parameter version of the model – i.e. it’s pretty dumb – compared to what you can actually run on your hardware.

I started running LLMs a couple months ago on my own hardware. I have a Framework Desktop that I ordered last year and also recently picked up a refurbished 24GB AMD RX 7900 XTX which I’m doing some performance testing against. The dGPU is much better for dense models, and slightly faster for MoE if I’m willing to run them at a lower quant – but uses more power and has annoying coil whine. The Framework Desktop uses ~100W under load, is quieter, and for the MoE models already runs them fast enough for most of my needs – so most of my LLM use happens on that system still.

For software: I’m using ollama on the Framework currently, but I want to replace it with just using llama.cpp directly eventually. I’ve been using llama-cli for testing the dGPU. I wrote my own chat client to interact with ollama as well as a few other programs for specific tasks.

I’ve been using the LLMs for a mix of research (both personal and professional), entertainment, practical coding tasks (mostly debugging and brainstorming, plus a bit of UI prototyping, automatic generation of sequence diagrams for documentation, and light scripting), as well as automation of tedious tasks.

As an example of the latter, people often send me requests to prepare data sets by email but don’t specify the sources they want precisely so I have to go match the name against the real name in our archives; LLMs are great for mapping the imperfect name – with typos, missing prefixes, incorrect addition of spaces, addition/removal of hyphens, etc. – to the exact name I actually need to pull the data off disk when given a lookup table to compare against.

As far as models go, I’m mostly using various Qwen 3.6 and Gemma4 variants. I have multiple versions of each for different purposes. llmfan46’s uncensored Qwen 3.6 35B-A3B @ Q6_K (from Hugging Face) is my default model currently.

Generally the professor in charge of the research group.

At this point, it’s been down long enough that setting up a Unix Surrealism community somewhere else is reasonable, IMO.

Tue 07 Apr 2026 11:25:59 AM EDT

There is a good chance that lemmy.sdf.org will return after much needed disk expansion. We ran out of space. Currently everything is preserved, we just need more disks in order to bring the site back online. Thank you for your patience.

https://lemmy.sdf.org/

Hmm. Yes. A community dedicated to Unix and Surrealism. That’d be quite a thing!

On a completely unrelated topic, it seems like the SDF lemmy needs more disks… 😏️

For ceramic, maybe see if someone can do a kintsugi fix for it instead of 3D printing?

Is this a Bayeskisser meme? 😛️

People have already covered most of the tools I typically use, but one I haven’t seen listed yet that is sometimes convenient is python3 -m http.server which runs a small web server that shares whatever is in the directory you launched it from. I’ve used that to download files onto my phone before when I didn’t have the right USB cables/adapters handy as well as for getting data out of VMs when I didn’t want to bother setting up something more complex.