FitMyLLM

Running LLMs on NVIDIA GeForce RTX 2070: What You Can Run

The NVIDIA GeForce RTX 2070 packs 8GB of GDDR6 with 448 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 else $150 buys. Or the full specifications.

Loading the model tables…

Running LLMs on NVIDIA GeForce RTX 2070: Complete Guide

The NVIDIA GeForce RTX 2070 has 8GB VRAM and 448 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 RTX 2070 specs page for detailed specifications, all compatible models, and speed estimates. Current price: $150.