The NVIDIA H100 NVL 94 GB packs 94GB of HBM3 with 3940 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 else $30,000 buys. Or the full specifications.
The NVIDIA H100 NVL 94 GB has 94GB VRAM and 3940 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 H100 NVL 94 GB specs page for detailed specifications, all compatible models, and speed estimates. Current price: $30000.