Community performance summary

Llama 3.3 70B

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

1 signed run · 0 verified · 1 tester
Median prompt291.49tok/s · 291.49 to 291.49
Median generation8.6tok/s · 8.6 to 8.6
Configurations1UD-IQ1_M
Last observedAug 22RDNA 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 tested1 groups
AMD Radeon PRO W6800X Duo ×21 run
macOS

macOS 26.6.1 Tahoe

Recorded evidence

Inspect every run.

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

1 to 8 of 1 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Llama 3.3 70BUD-IQ1_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
291.49tok/s
8.6tok/s
walrunsAug 22, 2026