The NVIDIA Tesla P10 packs 24GB of GDDR5X with 694 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 Tesla P10 has 24GB VRAM and 694 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 Tesla P10 specs page for detailed specifications, all compatible models, and speed estimates.