FitMyLLM

Running LLMs on NVIDIA P106-090: What You Can Run

The NVIDIA P106-090 packs 3GB of GDDR5 with 192 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 P106-090: Complete Guide

The NVIDIA P106-090 has 3GB VRAM and 192 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 P106-090 specs page for detailed specifications, all compatible models, and speed estimates.