The NVIDIA A800 PCIe 40 GB packs 40GB of HBM2e with 1560 GB/s of memory bandwidth, making it one of the best consumer GPUs for running local AI models. 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 A800 PCIe 40 GB has 40GB VRAM and 1560 GB/s memory bandwidth, making it one of the best consumer GPUs for running local AI models. This guide covers which LLMs fit, expected tok/s performance, and recommended settings.
See the full NVIDIA A800 PCIe 40 GB specs page for detailed specifications, all compatible models, and speed estimates.