FitMyLLM

Running LLMs on AMD Radeon Instinct MI8: What You Can Run

The AMD Radeon Instinct MI8 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 Instinct MI8: Complete Guide

The AMD Radeon Instinct MI8 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 Instinct MI8 specs page for detailed specifications, all compatible models, and speed estimates.