Community performance summary

Gemma 4 12B

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

12 signed runs · 2 verified · 5 testers
Median prompt339.59tok/s · 228.36 to 825.73
Median generation34.33tok/s · 13.3 to 53.4
Configurations3Q4_K_M · Q4_K_XL · UD-Q4_K_XL
Last observedJul 24GCN / Vega · GCN / Vega + RDNA 2 · RDNA 2 · Unknown

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.

Recorded evidence

Inspect every run.

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

1 to 8 of 12 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Gemma 4 12BQ4_K_M · Dense · comparison
RX 6950 XT16 GB VRAM
RDNA 2
595.7tok/s
53.4tok/s
Community testerJul 16, 2026
Gemma 4 12BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
757.14tok/s
48.49tok/s
Dolphins1972Jul 23, 2026
Gemma 4 12BUD-Q4_K_XL · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
Unknown
825.73tok/s
48.46tok/s
ToshLLM communityJul 24, 2026
Gemma 4 12BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
585.78tok/s
46.89tok/s
Dolphins1972Jul 18, 2026
Gemma 4 12BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
429.66tok/s
40.3tok/s
Flint IronstagJul 18, 2026
Gemma 4 12BUD-Q4_K_XL · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
337.18tok/s
34.66tok/s
ToshLLM LabJul 18, 2026
Gemma 4 12BQ4_K_XL · Dense · comparison
RX 6700 XT12 GB VRAM
RDNA 2
342tok/s
34tok/s
ToshLLM LabJul 15, 2026
Gemma 4 12BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega + RDNA 2
232.37tok/s
20.94tok/s
ToshLLM communityJul 20, 2026
Gemma 4 12BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega + RDNA 2
230.23tok/s
20.89tok/s
Flint IronstagJul 20, 2026
Gemma 4 12BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega + RDNA 2
328.49tok/s
19.1tok/s
Flint IronstagJul 20, 2026
Gemma 4 12BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon Vega ×231.97 GB VRAM
GCN / Vega
319.02tok/s
14.86tok/s
ToshLLM communityJul 23, 2026
Gemma 4 12BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega + RDNA 2
228.36tok/s
13.3tok/s
Flint IronstagJul 20, 2026