The NVIDIA A100 PCIe 40GB has 40GB VRAM and 1555 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 A100 PCIe 40GB specs page for detailed specifications, all compatible models, and speed estimates. Current price: $10000.