Community performance summary

GLM 4.5 Air

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

1 signed run · 0 verified · 1 tester
Median prompt199.11tok/s · 199.11 to 199.11
Median generation19.4tok/s · 19.4 to 19.4
Configurations1Q4_K_M
Last observedOct 8GCN / 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 Vega II Duo1 run→
macOS

macOS 15.7.7 Sequoia

Recorded evidence

Inspect every run.

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

1 to 8 of 1 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
GLM 4.5 AirQ4_K_M · MoE · Signed ToshLLM app · ncmoe 11 · amd-gpu · Metal · comparison
GCN / Vega
199.11tok/s
19.4tok/s
warriordr7Oct 8, 2026