FitMyLLM

Running LLMs on NVIDIA P102-100: What You Can Run

The NVIDIA P102-100 packs 5GB of GDDR5X with 440 GB/s of memory bandwidth, making it an entry-level 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.

Loading the model tables…

Running LLMs on NVIDIA P102-100: Complete Guide

The NVIDIA P102-100 has 5GB VRAM and 440 GB/s memory bandwidth, making it an entry-level option for running local AI models. This guide covers which LLMs fit, expected tok/s performance, and recommended settings.

See the full NVIDIA P102-100 specs page for detailed specifications, all compatible models, and speed estimates.