Community performance summary

GPT OSS 120B

1 GPU configurations measured with this model. Compare hardware differences, quantizations and every recorded result.

5 signed runs · 0 verified · 1 tester
Median prompt1493.82tok/s · 866.41 to 1554.92
Median generation72.82tok/s · 70.29 to 75.29
Configurations1MXFP4
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.

Hardware tested1 groups
AMD Radeon PRO W6800X Duo + AMD Radeon Pro Vega II5 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
GPT OSS 120BMXFP4 · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
1554.92tok/s
75.29tok/s
threadedNov 20, 2026
GPT OSS 120BMXFP4 · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
866.41tok/s
74.73tok/s
threadedNov 20, 2026
GPT OSS 120BMXFP4 · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
1494.48tok/s
72.82tok/s
threadedNov 20, 2026
GPT OSS 120BMXFP4 · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
1488.43tok/s
70.73tok/s
threadedNov 20, 2026
GPT OSS 120BMXFP4 · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2 + GCN / Vega
1493.82tok/s
70.29tok/s
threadedNov 20, 2026