Use this for claims about speed, latency, stability, and public rank.
Hardware check
Use the right answer for the question you actually have.
VRAM Check separates measured performance from planning guidance. Benchmark the machine you own, or explore a future GPU and model combination without presenting estimates as observed fact.
Use this to narrow hardware and model options before you spend.
Choose a path
Three useful questions. Three honest starting points.
The fastest route is not always the benchmark. It depends on whether the hardware already exists.
Run the shared benchmark locally when you need real throughput, timing, repeatability, and a report tied to the hardware in front of you.
Download the CLIUse the GPU catalog when the question is memory capacity, likely model fit, measured field signals, or which upgrade materially changes the ceiling.
Browse GPU profilesUse the model catalog when you already know your available memory and need to narrow the field by parameter count, quantization, context, or task.
Browse model profilesWhy no instant score?
A manual estimator should not look more certain than its inputs.
GPU name and VRAM alone cannot reliably reproduce drivers, backend behavior, power state, memory pressure, or system contention.
Model size, quantization, and memory architecture are valuable planning signals as long as the site keeps them separate from measured speed.
Every public result keeps its trust state visible so a compatibility estimate cannot silently become a ranked benchmark claim.