community pool / model answer

gemma-4-12B-it-AWQ-INT4

chat · cyankiwi/gemma-4-12B-it-AWQ-INT4

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB ×44-bit105.4 tok/sreported27- GB2,048vllm

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.