Community performance summary

Qwen3 4B × AMD Radeon RX 580

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

3 signed runs · 0 verified · 2 testers
Median prompt236.75tok/s · 232.34 to 271.35
Median generation37.72tok/s · 33.35 to 42.43
Configurations3Q4_0 · Q4_K_M · Q8_0
Last observedSep 22GCN / Vega

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 observed3 groups
Q4_01 runsQ4_K_M1 runsQ8_01 runs
macOS

macOS 15.7.3 Sequoia · macOS 15.7.9 Sequoia

Recorded evidence

Inspect every run.

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

1 to 8 of 3 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Qwen3 4BQ4_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega
236.75tok/s
42.43tok/s
cloudphreniaSep 22, 2026
Qwen3 4BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega
271.35tok/s
37.72tok/s
htweedieSep 5, 2026
Qwen3 4BQ8_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega
232.34tok/s
33.35tok/s
cloudphreniaSep 22, 2026