Community performance summary

Qwen3.8 27B

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

2 signed runs · 0 verified · 1 tester
Median prompt80.1tok/s · 17.54 to 142.67
Median generation7.59tok/s · 1.07 to 14.11
Configurations1Q4_K_M
Last observedAug 24GCN / 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.

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
Qwen3.8 27BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega
142.67tok/s
14.11tok/s
ToshLLM communityAug 24, 2026
Qwen3.8 27BQ4_K_M · Dense · Signed ToshLLM app · off · Metal · comparison
RDNA 1
17.54tok/s
1.07tok/s
ToshLLM communityAug 23, 2026