FitMyLLM

Running LLMs on NVIDIA GeForce 920MX: What You Can Run

The NVIDIA GeForce 920MX packs 2GB of DDR3 with 14 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 GeForce 920MX: Complete Guide

The NVIDIA GeForce 920MX has 2GB VRAM and 14 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 GeForce 920MX specs page for detailed specifications, all compatible models, and speed estimates.