FitMyLLM

Running LLMs on NVIDIA A100X: What You Can Run

The NVIDIA A100X packs 80GB of HBM2e with 2040 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 a budget buys. Or the full specifications.

Loading the model tables…

Running LLMs on NVIDIA A100X: Complete Guide

The NVIDIA A100X has 80GB VRAM and 2040 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 A100X specs page for detailed specifications, all compatible models, and speed estimates.