The NVIDIA Tesla P100 PCIe 12 GB packs 12GB of HBM2 with 549 GB/s of memory bandwidth, making it a capable option 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 Tesla P100 PCIe 12 GB has 12GB VRAM and 549 GB/s memory bandwidth, making it a capable option for running local AI models. This guide covers which LLMs fit, expected tok/s performance, and recommended settings.
See the full NVIDIA Tesla P100 PCIe 12 GB specs page for detailed specifications, all compatible models, and speed estimates.