FitMyLLM

Running LLMs on AMD Radeon Pro Duo: What You Can Run

The AMD Radeon Pro Duo packs 4GB of HBM with 512 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 AMD Radeon Pro Duo: Complete Guide

The AMD Radeon Pro Duo has 4GB VRAM and 512 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 AMD Radeon Pro Duo specs page for detailed specifications, all compatible models, and speed estimates.