Community performance summary

GLM 4.7 Flash 23B-A3B × AMD Radeon HD GFX10 Family Unknown Prototype

1 signed observations in one performance comparison. Open any run below to inspect its exact configuration and provenance.

1 signed run · 0 verified · 1 tester
Median prompt1341.71tok/s · 1341.71 to 1341.71
Median generation94.83tok/s · 94.83 to 94.83
Configurations1Q4_K_M
Last observedAug 6Unknown

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.

Quantizations observed1 groups
Q4_K_M1 runs
macOS

macOS 15.7.8 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 4.7 Flash 23B-A3BQ4_K_M · MoE · Signed ToshLLM app · ncmoe 1 · amd-gpu · Metal · comparison
Unknown
1341.71tok/s
94.83tok/s
ToshLLM communityAug 6, 2026