…Download

Community performance summary

AMD Radeon RX Vega 56

3 local models measured on this GPU configuration. Compare quantizations, configurations and the full observed performance range.

3 signed runs · 0 verified · 2 testers
Median prompt644.1tok/s · 258.72 to 743.66
Median generation40.54tok/s · 24.24 to 51.09
Configurations3Q4_0 · Q4_K_M · UD-Q4_K_XL
Last observedSep 6GCN / 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.

Models on this GPU3 groups
Qwen3 4B1 run→Hf E4B1 run→Gemma 4 12B1 run→
macOS

macOS 15.7.9 Sequoia · 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 3 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Qwen3 4BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon RX Vega 567.98 GB VRAM
GCN / Vega
743.66tok/s
51.09tok/s
ToshLLM communitySep 6, 2026
Hf E4BQ4_0 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon RX Vega 567.98 GB VRAM
GCN / Vega
644.1tok/s
40.54tok/s
めろんAug 25, 2026
Gemma 4 12BUD-Q4_K_XL · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon RX Vega 567.98 GB VRAM
GCN / Vega
258.72tok/s
24.24tok/s
めろんAug 25, 2026