community pool / model answer

GLM-4.7-Flash-4bit

chat · mlx-community/GLM-4.7-Flash-4bit

77.5 tok/s · model median · 1 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M5 Pro 64GB4-bit77.5 tok/sreported26617.2 GB2,048mlx

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.