Community performance summary

Llama 3.2 1B × AMD Radeon PRO W6800X

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

2 signed runs · 0 verified · 1 tester
Median prompt5730.79tok/s · 5655.79 to 5805.79
Median generation260.83tok/s · 233.02 to 288.64
Configurations2Q4_K_M · Q8_0
Last observedJul 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 observed2 groups
Q4_K_M1 runsQ8_01 runs
macOS

macOS 15.7.7 Sequoia

Recorded evidence

Inspect every run.

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

1 to 8 of 2 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
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 1BQ8_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
5805.79tok/s
233.02tok/s
BirdsLikeWiresJul 22, 2026