Community performance summary

Qwen3 Coder 30B-A3B

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

8 signed runs · 0 verified · 5 testers
Median prompt507.17tok/s · 71.18 to 1293.17
Median generation40.5tok/s · 1.09 to 94.98
Configurations1Q4_K_M
Last observedSep 8GCN / Vega · RDNA 2 · RDNA 2 + GCN / 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 tested7 groups
AMD Radeon RX 5801 runAMD Radeon Pro Vega II2 runsAMD Radeon RX 6900 XT + AMD Radeon Vega1 runAMD Radeon Pro 5801 runAMD Radeon Vega ×21 runAMD Radeon PRO W6800X1 runRX 6950 XT1 run
macOS

macOS 14.7.5 Sonoma · macOS 15.7.5 Sequoia · macOS 15.7.9 Sequoia · macOS 26.5.2 Tahoe · macOS 26.6.2 Tahoe

Recorded evidence

Inspect every run.

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

1 to 8 of 8 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Qwen3 Coder 30B-A3BQ4_K_M · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
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
617.65tok/s
54.89tok/s
simmc303Aug 28, 2026
Qwen3 Coder 30B-A3BQ4_K_M · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega
346.78tok/s
53.32tok/s
gervaiscoquilJul 18, 2026
Qwen3-Coder 30B A3BQ4_K_M · MoE · ncmoe 23 · comparison
RX 6950 XT16 GB VRAM
RDNA 2
587.3tok/s
47.8tok/s
Community testerJul 16, 2026
Qwen3 Coder 30B-A3BQ4_K_M · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
807.25tok/s
33.2tok/s
ToshLLM communityAug 10, 2026
Qwen3 Coder 30B-A3BQ4_K_M · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon Vega ×231.97 GB VRAM
GCN / Vega
427.04tok/s
23.94tok/s
ToshLLM communityJul 23, 2026
Qwen3 Coder 30B-A3BQ4_K_M · MoE · Signed ToshLLM app · ncmoe 35 · amd-gpu · Metal · comparison
GCN / Vega
71.18tok/s
9.83tok/s
ToshLLM communityAug 10, 2026
Qwen3 Coder 30B-A3BQ4_K_M · MoE · Signed ToshLLM app · ncmoe 44 · amd-gpu · Metal · comparison
GCN / Vega
135.45tok/s
1.09tok/s
htweedieSep 8, 2026