community pool / model answer

gemma-4-31B-it-qat-GGUF

chat · unsloth/gemma-4-31B-it-qat-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M5 Pro 24GB4-bit27.8 tok/sreported691- GB8,192llama.cpp
RTX 5090 32GB4-bit207.6 tok/sreported7830.2 GB200,000llama.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.