community pool / model answer

gemma-4-26B-A4B-it-GGUF

chat · lmstudio-community/gemma-4-26B-A4B-it-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit69.5 tok/sreported-17.3 GB100,000llama.cpp
RTX 5090 32GB4-bit209.8 tok/sreported79- GB2,048lmstudio

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.