community pool / model answer

EXAONE-3.5-7.8B-Instruct

chat · LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct

22.5 tok/s · model median · 4 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RX 570 4GB ×24-bit22.5 tok/smeasured56- 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.