LOL

Perhaps not, I did recently import a Japanese psvita that I hacked and am side eyeing the FFX remaster 😂

I’m coming back to wow after dropping it during BfA and played a bit of the beta. I rolled a skyborn mage and really enjoyed it. Def want a druid next

I’ve always admired final fantasy from afar, whenever I tried to play any of the entries I usually bounced off. I got the furthest in ffx, but recently spent a lot of time in ffxiv.

Something about the style of resonance grabbed me and I decided to give it a shot. My party is level 26 now and I quite like what the game has to offer and it will likely be the first final fantasy game I finish lol

Dropped of my ballot for Abdul to the official drop box at city hall over the weekend.

Oh that sounds rad lol. I was considering the possibility of building a setup within nixos using vfio to declare and configure VMs. I like your integration with systemd, that’s clever

This person on huggingface makes excellent space saving models using APEX quantizations. They produced this one to fit on gpus with 16gb of vram or less.

https://huggingface.co/mudler/Qwen3.8-27B-APEX-GGUF

How did you configure DeepSeek harness? I’m guessing a flake would be useful.

I read your post and ended up finding this repo: https://github.com/numtide/llm-agents.nix

I’m considering deploying it for testing in a nix container. 🤔

Listen to Pray for Plagues on your streaming service https://tidal.com/track/514582390/u

Though I think being lumped in with Ohio is much worse. 🤢🤮

This one is a Mixture of Experts model (40B total weight, 2.5B active during token generation). Inference engines like llama.cpp have flags you can pass to offload the lesser used experts to system RAM.

It’s slower than having the entire model resident in VRAM, but generally pretty usable.

I’ve been using NixOS/nix containers to host some llama.cpp servers and Hermes Agent. Though I wrote a flake to get Project Maya working so I can serve GLM-5.3-Flash and in legit blown away by how well it works. It’s a fork of strata/llama.cpp that focuses on where the relevant experts are loaded and has a neat dashboard to track their use. https://github.com/mw00/project-maya

My server is assembled into an openair mining rig with a Tesla P40, RTX 3080, and a few Tesla V100s. All of which I bought used off eBay.

I purchased my first domain to self host a matrix server that I can access via my phone and I also have tailscale set up so I can ssh into the server via my laptop while traveling