Community performance summary

Gemma 3 4B

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

3 signed runs · 2 verified · 2 testers
Median prompt1146.18tok/s · 899.15 to 1168
Median generation87.63tok/s · 62.76 to 90
Configurations1Q4_K_M
Last observedJul 20RDNA 2

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 tested2 groups
AMD Radeon RX 6600 XT1 runAMD Radeon RX 6700 XT2 runs
macOS

macOS 15.7.7 Sequoia · macOS 26.5.1 Tahoe

Recorded evidence

Inspect every run.

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

1 to 8 of 3 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Gemma 3 4BQ4_K_M · Dense · comparison
RX 6700 XT12 GB VRAM
RDNA 2
1168tok/s
90tok/s
ToshLLM LabJul 15, 2026
Gemma 3 4BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
1146.18tok/s
87.63tok/s
ToshLLM LabJul 17, 2026
Gemma 3 4BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
899.15tok/s
62.76tok/s
ArdentwheelJul 20, 2026