GLM 4.7 Flash 23B-A3B

Q4_K_M running on AMD Radeon HD GFX10 Family Unknown Prototype with macOS 15.7.8 Sequoia

PERFORMANCE / TOKENS PER SECONDUnknown

Prompt processing1341.71tok/s

#19 in index

Token generation94.83tok/s

#20 in index

Run fingerprint

Enough context to make the number useful.

ModelGLM 4.7 Flash 23B-A3BMoE architecture

QuantizationQ4_K_MExact submitted variant

GPUAMD Radeon HD GFX10 Family Unknown Prototype15.98 GB VRAM

GPU architectureUnknownMetal backend

Test context512prompt tokens

Model familyMoESigned ToshLLM app · ncmoe 1 · amd-gpu · Metal

Prompt processing and generation are reported separately so memory bandwidth and decode behavior stay visible.

Quantization, GPU family, VRAM and context travel with the result instead of being hidden behind one score.

This result remains explicitly labeled as a community submission.