community pool / model answer

Qwen3.5-4B-Uncensored-HauhauCS-Aggressive

chat · HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive

82.9 tok/s · model median · 1 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB4-bit82.9 tok/sreported1,6305.1 GB4,608llama.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.