community pool / model answer

Qwopus3.5-27B-v3-GGUF

chat · Jackrong/Qwopus3.5-27B-v3-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Radeon RX 7900 XTX 24GB4-bit28.6 tok/sreported-14.5 GB640llama.cpp
RTX 3090 24GB4-bit26 tok/smeasured7,951- GB131,072llama.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.