…Download

Community performance summary

Smollm3 3B

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

2 signed runs · 0 verified · 1 tester
Median prompt349.9tok/s · 315.9 to 383.9
Median generation35.94tok/s · 28.55 to 43.32
Configurations2BF16 · Q4_K_M
Last observedSep 14GCN / 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 RX 5802 runs→
macOS

macOS 15.7.3 Sequoia

Recorded evidence

Inspect every run.

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

1 to 8 of 2 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Smollm3 3BQ4_K_M · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon RX 5808 GB VRAM
GCN / Vega
315.9tok/s
43.32tok/s
cloudphreniaSep 14, 2026
Smollm3 3BBF16 · Dense · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon RX 5808 GB VRAM
GCN / Vega
383.9tok/s
28.55tok/s
cloudphreniaSep 14, 2026