Community performance summary

Qwen3 Coder 30B-A3B × Vega II + 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 prompt819.98tok/s · 346.78 to 1293.17
Median generation74.15tok/s · 53.32 to 94.98
Configurations1Q4_K_M
Last observedJul 22GCN / Vega + RDNA 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
Q4_K_M2 runs
macOS

macOS 26.5.2 Tahoe

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
Qwen3 Coder 30B-A3BQ4_K_M · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega + RDNA 2
1293.17tok/s
94.98tok/s
gervaiscoquilJul 22, 2026
Qwen3 Coder 30B-A3BQ4_K_M · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega + RDNA 2
346.78tok/s
53.32tok/s
gervaiscoquilJul 18, 2026