The NVIDIA A40 48GB packs 48GB of GDDR6 with 696 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 $4,650 buys. Or the full specifications.
The NVIDIA A40 48GB has 48GB VRAM and 696 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 A40 48GB specs page for detailed specifications, all compatible models, and speed estimates. Current price: $4650.