Community performance summary

Qwen3Vl 4B

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

1 signed run · 0 verified · 1 tester
Median prompt239.43tok/s · 239.43 to 239.43
Median generation19.86tok/s · 19.86 to 19.86
Configurations1Q4_K_M
Last observedAug 3GCN / 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.

Hardware tested1 groups
AMD Radeon Pro 5801 run
macOS

macOS 14.7.5 Sonoma

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
Qwen3Vl 4BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega
239.43tok/s
19.86tok/s
ToshLLM communityAug 3, 2026