Show HN: NixOS-DGX-Spark – Nix and NixOS on the DGX Spark

5 comments

• hamza7159 0 minutes ago
  Your product has great potential and offers some useful features, but I encountered a few issues that could be improved. Please contact me so I can share detailed feedback and suggest the changes I'd like to see.

  Email: contact@rforrank.com
• thenobsta 3 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 1 minute ago
  Thanks for sharing, saving this for when I get a DGX Spark
• 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 32 minutes ago
    What quant are you using, and what tps are you getting with K3?
    [-]
    • redrove 1 minute 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 in 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.
• nixie-tubes 1 hour ago
  This has been amazingly helpful for managing my DGX Spark! Thank you for all your time and effort into this project!
  [-]
  • graham33 1 hour ago
    Good to hear, thanks!