7 comments

  • hamandcheese 32 minutes ago
    Slightly off topic, but Claude Code (and likely other models/harnesses) are incredibly effective at Nix. It can trivially self-verify, without side effects, which is a perfect match for an LLM.

    If you've ever been put off by the difficulty of the language, it's worth checking it out again with AI assistance.

    • graham33 15 minutes ago
      Agreed, Claude has helped a lot with this project, and being able to iterate without side effects for system configuration changes is really a game changer for agents.
    • Loeffelmann 26 minutes ago
      I also love how with the right system prompt they can pull in tooling for what they currently need via a nix shell
    • colordrops 29 minutes ago
      I've one-shotted custom distributions built with Nix using AI. It's crazy how well AI and Nix fit together.
  • redrove 1 hour ago
    Been running this on a few Asus GX10 machines with k3s on top, it’s been great. I’m running the new deepseek.

    Thank you for your work!

    • pixelesque 1 hour ago
      What quant are you using, and what tps are you getting with K3?
      • redrove 50 minutes ago
        The FP8 version from DeepSeek themselves [0], around 1800 tps prefill and 45 tokens per second decode.

        I’ve been running a custom VLLM image with b12x as well as nvfp4_ds_mla.

        I would say it’s quite fantastic in day to day, I use it mostly in Hermes and sometimes for coding.

        I have qwen 3.6 27b on an rtx 6000 pro as well so I use that as a workhorse in pi with DS as a reviewer/planner.

        [0] https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731

        Edit: I think you may have misread my post. k3s is NOT kimi k3, and I did mention I was running deepseek.

        • pixelesque 1 minute ago
          Thanks - yeah, sorry, I mis-read that as you using both DS and K3...
  • ronef 46 minutes ago
    Huge plus to anyone interested in the space to check out what Graham built here!

    If anyone is also interested on Nix/CUDA/Capital Markets/Flox, we recently did another case study in the space - https://flox.dev/blog/deploying-hardened-flox-nvidia-cuda-st...

  • thenobsta 52 minutes ago
    This is incredible. I have a Jetson lying around and will try to it out on this. I use it to play with vision models, not LLMs, and have been wanting a better way to manage the machine.
  • haunter 50 minutes ago
    Thanks for sharing, saving this for when I get a DGX Spark
  • nixie-tubes 2 hours ago
    This has been amazingly helpful for managing my DGX Spark! Thank you for all your time and effort into this project!
    • graham33 2 hours ago
      Good to hear, thanks!
  • hamza7159 48 minutes ago
    [dead]