Community performance summary

Google Gemma 4 31B

1 GPU configurations measured with this model. Compare hardware differences, quantizations and every recorded result.

1 signed run · 0 verified · 1 tester
Median prompt101.03tok/s · 101.03 to 101.03
Median generation14.91tok/s · 14.91 to 14.91
Configurations1Q4_0
Last observedSep 22Apple Silicon

What the results show

One clear view.
Every recorded run.

Measurements from comparable hardware and models are presented together. Medians show typical performance, while every signed run remains available below for inspection and sharing.

Hardware tested1 groups
Apple M1 Max1 run→
macOS

macOS 27.0

Recorded evidence

Inspect every run.

Open any result to review its exact hardware, model configuration, measurements and submission details.

1 to 8 of 1 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Google Gemma 4 31BQ4_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
Apple M1 Max51.84 GB VRAM
Apple Silicon
101.03tok/s
14.91tok/s
simmc303Sep 22, 2026