FitMyLLM

Running LLMs on NVIDIA A100 PCIe 80GB: What You Can Run

The NVIDIA A100 PCIe 80GB packs 80GB of HBM2e with 1935 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 $10,000 buys. Or the full specifications.

Loading the model tables…

Running LLMs on NVIDIA A100 PCIe 80GB: Complete Guide

The NVIDIA A100 PCIe 80GB has 80GB VRAM and 1935 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 A100 PCIe 80GB specs page for detailed specifications, all compatible models, and speed estimates. Current price: $10000.