FitMyLLM

Running LLMs on Intel Xeon Phi 5120D: What You Can Run

The Intel Xeon Phi 5120D packs 8GB of GDDR5 with 320 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 Intel Xeon Phi 5120D: Complete Guide

The Intel Xeon Phi 5120D has 8GB VRAM and 320 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 Intel Xeon Phi 5120D specs page for detailed specifications, all compatible models, and speed estimates.