GLM 4.5 Air

Q4_K_M running on AMD Radeon Pro Vega II Duo with macOS 15.7.7 Sequoia

PERFORMANCE / TOKENS PER SECONDGCN / Vega

Prompt processing199.11tok/s

#248 in index

Token generation19.4tok/s

#256 in index

Run fingerprint

Enough context to make the number useful.

ModelGLM 4.5 AirMoE architecture

QuantizationQ4_K_MExact submitted variant

GPUAMD Radeon Pro Vega II Duo63.97 GB VRAM

GPU architectureGCN / VegaMetal backend

Test context512prompt tokens

Model familyMoESigned ToshLLM app · ncmoe 11 · amd-gpu · Metal

ToshLLM versionv0.87.18App version used to capture and sign this run

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.