FitGPUPickerBenchmarksMethodologySubmit resultsAbout

Measured benchmarks

Real measurements using Ollama (median of 3 runs, 4K context, 256 generated tokens). Verified (our rigs) rows are measured on our own machines. Community rows are submitted by readers with the same script and reviewed before publishing, but we cannot re-check their hardware. Submit your results.

Results

SourceRigGPU(s)ModelQuantPrompt tok/sGen tok/sDate
No measured results yet.