The RTX Pro 6000 packs 96GB of GDDR7 with 1792 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 $8,565 buys. Or the full specifications.
The RTX Pro 6000 has 96GB VRAM and 1792 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 RTX Pro 6000 specs page for detailed specifications, all compatible models, and speed estimates. Current price: $8565.