…Download

Community performance summary

AMD Radeon Vega

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

6 signed runs · 0 verified · 2 testers
Median prompt259.22tok/s · 230.23 to 552.59
Median generation32.33tok/s · 20.89 to 48.8
Configurations1Q4_K_M
Last observedJul 20GCN / 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 GPU5 groups
Qwen3 4B1 run→Meta Llama 3.1 8B1 run→Qwen3 8B1 run→GLM 4 9B1 run→Gemma 4 12B2 runs→
macOS

macOS 26.5 Tahoe

Recorded evidence

Inspect every run.

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

1 to 8 of 6 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Qwen3 4BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon Vega15.98 GB VRAM
GCN / Vega
552.59tok/s
48.8tok/s
ToshLLM community✓Jul 20, 2026
Meta Llama 3.1 8BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon Vega15.98 GB VRAM
GCN / Vega
277.72tok/s
34.4tok/s
ToshLLM community✓Jul 20, 2026
Qwen3 8BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon Vega15.98 GB VRAM
GCN / Vega
266.06tok/s
33.27tok/s
ToshLLM community✓Jul 20, 2026
GLM 4 9BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon Vega15.98 GB VRAM
GCN / Vega
252.37tok/s
31.39tok/s
Flint Ironstag✓Jul 20, 2026
Gemma 4 12BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon Vega15.98 GB VRAM
GCN / Vega
232.37tok/s
20.94tok/s
ToshLLM community✓Jul 20, 2026
Gemma 4 12BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon Vega15.98 GB VRAM
GCN / Vega
230.23tok/s
20.89tok/s
Flint Ironstag✓Jul 20, 2026