community pool / model answer

gemma-4-E4B-it-qat-q4_0-gguf

chat · google/gemma-4-E4B-it-qat-q4_0-gguf

58.6 tok/s · model median · 3 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB4-bit88.1 tok/sreported1,3714.9 GB4,608llama.cpp
RX 570 4GB4-bit27.5 tok/sreported326- GB2,048llama.cpp
RX 570 4GB ×24-bit33.2 tok/sreported242- 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.