NVIDIA pitches RTX Spark for local coding agents, ships open Nemotron 3.5 Bolt 74B in 24GB
As of Oct 16, RTX Spark laptops (GB10, up to 128GB unified memory) are available with local-model support tuned for GitHub Copilot, Pi, Hermes, OpenClaw, and JetBrains Junie Local; compact desktops follow in November. NVIDIA also released Nemotron 3.5 Bolt 74B-A9B, a fully open 2-bit MoE that fits in 24GB and runs on llama.cpp, vLLM, Ollama, Unsloth, and LM Studio.