Community performance summary

Vega ×6 + 580X

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

2 signed runs · 0 verified · 1 tester

Median prompt553.35tok/s · 548.52 to 558.18

Median generation32.16tok/s · 31.45 to 32.86

Configurations1Q4_K_M

Last observedSep 10GCN / 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 GPU2 groups

Meta Llama 3.1 8B1 run→Qwen3 8B1 run→

Recorded evidence

Inspect every run.

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

ModelAppSort

1 to 8 of 2 configurations

Verified benchmark Community submission

Model / quant	Hardware	Architecture	Prompt	Generation	Source
Meta Llama 3.1 8BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon Vega ×6 + AMD Radeon Pro 580X103.91 GB VRAM	GCN / Vega	558.18tok/s	32.86tok/s	Flint IronstagSep 10, 2026
Qwen3 8BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison	AMD Radeon Vega ×6 + AMD Radeon Pro 580X103.91 GB VRAM	GCN / Vega	548.52tok/s	31.45tok/s	Flint IronstagSep 10, 2026

Vega ×6 + 580X

One clear view.Every recorded run.

Inspect every run.

No matching runs

One clear view.
Every recorded run.