Community performance summary

Llama 3.3 70B × AMD Radeon PRO W6800X Duo ×2

1 signed observations in one performance comparison. Open any run below to inspect its exact configuration and provenance.

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.

Quantizations observed1 groups
UD-IQ1_M1 runs
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