community pool / model answer

gemma-4-12B-it-qat-GGUF

chat · unsloth/gemma-4-12B-it-qat-GGUF

79 tok/s · model median · 12 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M5 Pro 24GB4-bit67.2 tok/sreported250- GB2,048llama.cpp
RTX 3060 12GB4-bit79 tok/sreported1,2459.5 GB65,536llama.cpp
RTX 3090 24GB4-bit104.1 tok/smeasured-11.8 GB262,144llama.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.