community pool / model answer

Qwopus3.6-27B-v2-GGUF

chat · Jackrong/Qwopus3.6-27B-v2-GGUF

18.2 tok/s · model median · 11 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 2080 Ti 11GB ×24-bit20.1 tok/sreported1,40919.3 GB98,304llama.cpp
RTX 3060 12GB ×24-bit17.7 tok/smeasured18,59219.5 GB131,072llama.cpp
RTX 3090 24GB ×26-bit56.4 tok/sreported533- GB262,144llama.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.