community pool / model answer

models-moved

chat · ggml-org/models-moved

10,550.8 tok/s · model median · 2 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
AMD Ryzen 7 9800X3D3-bit16,740.7 tok/sreported42- GB2,048llama.cpp
RTX 5090 32GB3-bit4,360.9 tok/sreported1- GB2,048llama.cpp

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.