Community performance summary

Qwen2.5 Coder 7B

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

4 signed runs · 0 verified · 4 testers
Median prompt141.76tok/s · 48.27 to 495.6
Median generation22.41tok/s · 3.55 to 52.31
Configurations1Q4_K_M
Last observedSep 11GCN / Vega · RDNA 1

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 tested4 groups
AMD Radeon Pro 560X1 runAMD Radeon RX 5801 runAMD Radeon Pro 5801 runAMD Radeon RX 5700 XT1 run
macOS

macOS 14.7.5 Sonoma · macOS 15.6 Sequoia · 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 4 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Qwen2.5 Coder 7BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 1
495.6tok/s
52.31tok/s
blacklizardJul 31, 2026
Qwen2.5 Coder 7BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega
138.96tok/s
30.07tok/s
cloudphreniaSep 10, 2026
Qwen2.5 Coder 7BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega
144.55tok/s
14.75tok/s
ToshLLM communityAug 3, 2026
Qwen2.5 Coder 7BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega
48.27tok/s
3.55tok/s
mitchdeSep 11, 2026