community pool / model answer

gemma-4-E4B-it-GGUF

chat · lmstudio-community/gemma-4-E4B-it-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit62.1 tok/sreported-7.8 GB128,000llama.cpp
RTX 5090 32GB8-bit161.5 tok/sreported64- 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.