GpuTps

GPU TPS Calculator & Local AI Compatibility

Want to know which local AI models your GPU can actually run — and how fast?

This app is built for one clear purpose: help you discover the best local LLMs for your hardware and show you the real-world tokens-per-second (TPS) performance you can expect.

What you can do:

• Check any GPU and instantly see which local AI models it can run

• See estimated TPS (tokens per second) for popular models

• Look up a specific AI model and find out which GPUs are compatible

• Compare performance across different hardware

• Plan your local AI setup with confidence before downloading large models

Whether you’re running models with Ollama, LM Studio, text-generation-webui, or any other local inference tool, this app helps you avoid wasting time on models that are too heavy for your GPU.

Simply select your GPU or search for a model — and get clear, practical answers about compatibility and speed.

Perfect for AI enthusiasts, developers, and anyone running local large language models.