FitMyLLM

Running LLMs on NVIDIA Jetson T4000: What You Can Run

The NVIDIA Jetson T4000 packs 64GB of LPDDR5X with 273 GB/s of memory bandwidth, making it one of the fastest cards you can run a local model on. 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 Jetson T4000: Complete Guide

The NVIDIA Jetson T4000 has 64GB VRAM and 273 GB/s memory bandwidth, making it one of the fastest cards you can run a local model on. This guide covers which LLMs fit, expected tok/s performance, and recommended settings.

See the full NVIDIA Jetson T4000 specs page for detailed specifications, all compatible models, and speed estimates.