The NVIDIA Tesla K20s packs 5GB of GDDR5 with 208 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.
The NVIDIA Tesla K20s has 5GB VRAM and 208 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 Tesla K20s specs page for detailed specifications, all compatible models, and speed estimates.