Brian CaffeyJBC
  • Blog
  • Contact
🏷️ All Tags 🏷️
k8s 🏷️ (2)
  • My first LLM eval end-to-end: scoring NVIDIA's Nemotron-3-Nano-Omni-30B (NVFP4) on MMLU 5-shot via vLLM on a DGX Spark, with interactive charts breaking down where it's strong, where it's weak, and how confident it is.

    Running MMLU 5-shot on Nemotron Nano Omni with a DGX Spark

    My first LLM eval end-to-end: scoring NVIDIA's Nemotron-3-Nano-Omni-30B (NVFP4) on MMLU 5-shot via vLLM on a DGX Spark, with interactive charts breaking down where it's strong, where it's weak, and how confident it is.

    ai 🏷️
    llm 🏷️
    eval 🏷️
    mmlu 🏷️
    vllm 🏷️
    nemotron 🏷️
    dgx-spark 🏷️
    k8s 🏷️
    localmaxxing 🏷️

    Last updated June 18, 2026

  • An overview of my experience with the Google CodeLabs tutorial for deploying an AI model on GKE with NVIDIA NIM

    Deploying an AI model on GKE with NVIDIA NIM

    An overview of my experience with the Google CodeLabs tutorial for deploying an AI model on GKE with NVIDIA NIM

    nvidia 🏷️
    ai 🏷️
    llm 🏷️
    nim 🏷️
    gcp 🏷️
    gke 🏷️
    k8s 🏷️
    https://x.com/briancaffey/status/2025106078543888633

    Last updated February 20, 2026


Join my mailing list to get updated whenever I publish a new article.

Thanks for checking out my site!
© 2026 Brian Caffey