Community performance summary

Qwen3.8 27B × W6800X Duo + Vega II

5 signed observations in one performance comparison. Open any run below to inspect its exact configuration and provenance.

5 signed runs · 0 verified · 1 tester
Median prompt468.43tok/s · 316.14 to 568.6
Median generation22.29tok/s · 15.82 to 22.94
Configurations1Q8_0
Last observedNov 20RDNA 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.

Quantizations observed1 groups
Q8_05 runs
macOS

macOS 26.7.3 Tahoe

Recorded evidence

Inspect every run.

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

1 to 8 of 5 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Qwen3.8 27BQ8_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
468.43tok/s
22.94tok/s
threadedNov 20, 2026
Qwen3.8 27BQ8_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
496.44tok/s
22.73tok/s
threadedNov 20, 2026
Qwen3.8 27BQ8_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
568.6tok/s
22.29tok/s
threadedNov 20, 2026
Qwen3.8 27BQ8_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
316.14tok/s
16.61tok/s
threadedNov 20, 2026
Qwen3.8 27BQ8_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
340.56tok/s
15.82tok/s
threadedNov 20, 2026