Free LLM calculators that run in your browser

How much GPU memory a model needs, how fast it writes on your hardware and what fits on your GPU, read from the model files on Hugging Face. Nothing to install, no sign-up.

• LLM Speed Calculator Estimate how many tokens per second an LLM writes on your GPU or Mac, from memory bandwidth, the active parameters and the context length. Works with any model on Hugging Face.
• LLM VRAM Calculator Estimate how much GPU memory an LLM needs to run: weights, KV cache and overhead for any quantization and context length. Load any model from Hugging Face.