community pool / model answer

Qwopus3.8-27B-Flash-GGUF

chat · Jackrong/Qwopus3.8-27B-Flash-GGUF

27.6 tok/s · model median · 2 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M5 Max 128GB4-bit26.5 tok/sreported460- 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.