The NVIDIA GB10 packs 128GB of LPDDR5X with 273 GB/s of memory bandwidth, making it one of the fastest cards you can run a local model on. Here is which models fit, how fast they run, and what quantisation gives the best balance of quality and speed.
Already have it? Find the best model for it. Still choosing? See what a budget buys. Or the full specifications.
The NVIDIA GB10 has 128GB VRAM and 273 GB/s memory bandwidth, making it one of the fastest cards you can run a local model on. This guide covers which LLMs fit, expected tok/s performance, and recommended settings.
See the full NVIDIA GB10 specs page for detailed specifications, all compatible models, and speed estimates.