community pool / model answer

Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive

chat · HauhauCS/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX PRO 6000 Blackwell Workstation Edition 96GB4-bit86.9 tok/sreported20,36275 GB65,536llama.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.