Ali Asif

The AI log, by topic

DGX Spark: what I’ve logged

DGX Spark comes up in 2 posts of my AI log, from October 2026 to October 2026, and each item below links to the primary source. The sources come from NVIDIA, filed under agents and coding, open weights and image, video, world.

Items that mention DGX Spark

  1. NVIDIA 30 Oct 2026

    Run AI Models for Edge Application Development with Just a Few Commands

    TensorRT Edge-LLM runs Nemotron-3.5 Lightning on a 64GB DGX Spark through the trtedge CLI, and DSpark speculative decoding raises mean speed from 73.4 to 126.9 tokens per second on HumanEval prompts.

    Primary source

  2. NVIDIA 22 Oct 2026

    Running Frontier-Class AI Models Across 8 NVIDIA DGX Spark Nodes

    Official eight-node DGX Spark clusters give 1 TB of unified memory, enough to serve the full GLM 5.3 locally, with decode on a 27B model scaling from about 12 to 52 tokens per second.

    Primary source

Posts that cover DGX Spark

October 20262 entries

  1. 31 Oct 2026NemoClaw agents, TensorRT Edge-LLM, Dynamo AICR, MOSS 2-stepAgents and coding · Open weights · Image, video, world
  2. 22 Oct 2026Agent Skills, OlmoEarth v1.3, ForTy, DGX Spark, Granite ensembleAgents and coding · Open weights · Science