Community performance summary

Llama 3.2 1B

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

7 signed runs · 1 verified · 3 testers
Median prompt5805.79tok/s · 2994 to 8153.51
Median generation266.14tok/s · 233.02 to 297.01
Configurations2Q4_K_M · Q8_0
Last observedJul 23RDNA 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 tested3 groups
AMD Radeon RX 6900 XT ×24 runsAMD Radeon PRO W6800X2 runsRX 6700 XT1 run
macOS

macOS 15.7.7 Sequoia · macOS 26.5.2 Tahoe

Recorded evidence

Inspect every run.

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

1 to 8 of 7 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
8088.69tok/s
297.01tok/s
Dolphins1972Jul 23, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
5655.79tok/s
288.64tok/s
BirdsLikeWiresJul 22, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
5476.18tok/s
268.45tok/s
Dolphins1972Jul 18, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
8153.51tok/s
266.14tok/s
Dolphins1972Jul 23, 2026
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
8077.28tok/s
265.52tok/s
Dolphins1972Jul 23, 2026
Llama 3.2 1BQ4_K_M · Dense · comparison
RX 6700 XT12 GB VRAM
RDNA 2
2994tok/s
250tok/s
ToshLLM LabJul 15, 2026
Llama 3.2 1BQ8_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
5805.79tok/s
233.02tok/s
BirdsLikeWiresJul 22, 2026