community pool / model answer

Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced

chat · HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB4-bit38.4 tok/sreported3,3319.9 GB4,608llama.cpp
Ryzen AI Max 395 128GB4-bit24.8 tok/sreported2169.7 GB4,096llama.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.