community pool / model answer

gemma-4-coder-gguf

code · jgebbeken/gemma-4-coder-gguf

37.1 tok/s · model median · 6 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit37.1 tok/smeasured3,4488.4 GB32,768llama.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.