Community performance summary

Carnice Qwen3.6 MoE 35B

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

2 signed runs · 0 verified · 1 tester
Median prompt86.13tok/s · 72.63 to 99.63
Median generation9.79tok/s · 5.05 to 14.52
Configurations1Q3_K_M
Last observedAug 2Unknown

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 Ellesmere Prototype2 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
Carnice Qwen3.6 MoE 35BQ3_K_M · MoE · Signed ToshLLM app · ncmoe 30 · amd-gpu · Metal · comparison
Unknown
99.63tok/s
14.52tok/s
1252erAug 2, 2026
Carnice Qwen3.6 MoE 35BQ3_K_M · MoE · Signed ToshLLM app · ncmoe 3 · amd-gpu · Metal · comparison
Unknown
72.63tok/s
5.05tok/s
1252erAug 2, 2026