Community performance summary

RX 6900 XT + Vega

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

5 signed runs · 0 verified · 1 tester
Median prompt883.21tok/s · 802.94 to 3047.25
Median generation42.52tok/s · 30.44 to 113.04
Configurations2F16 · Q4_K_M
Last observedAug 21RDNA 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.

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
Llama 3.2 1BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
3047.25tok/s
113.04tok/s
ToshLLM communityAug 10, 2026
GPT OSS 20BF16 · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
802.94tok/s
43.92tok/s
ToshLLM communityAug 11, 2026
Qwen3 4BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
1216.76tok/s
42.52tok/s
ToshLLM communityAug 10, 2026
Qwen3 Coder 30B-A3BQ4_K_M · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
807.25tok/s
33.2tok/s
ToshLLM communityAug 10, 2026
Gemma4 26B-A4BQ4_K_M · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
883.21tok/s
30.44tok/s
ToshLLM communityAug 21, 2026