Z.ai
Z.ai
/GLM-4.5 Air

Quantizations

QuantQuantized bySizeDecodePrefillScoreActions
MLX Community
MLX Community
43.6 GB35.7 tok/s297.1 tok/sRuns ok

Device Comparison

Results include trials with 4,096 input tokens and 1,024 output tokens only.

Decode / Prefill Speeds

1 device