[bmdpat]
Rig Fit Report $12

§ 001 / RIG FIT REPORT

Get a launch command for your rig.

Choose your GPU, system RAM and model. Get a recommended quant, a specific llama.cpp command and the memory budget behind it.

§ 002 / YOUR REPORT

Your rig, your report

$12 once

Your hardware and model

One payment. Your report on this page and by email. No account, subscription or install to buy.

§ 003 / BEFORE YOU RUN

Before you run the command

This report supports the NVIDIA GPUs and models listed above. Running the command requires a current CUDA-enabled llama.cpp build. Memory fit is estimated; it is not a measured speed result or a guarantee of successful execution.