GLM-4.5 Air

GLM-4.5 Air is useful to evaluate because it combines a specific architecture, license and operating envelope rather than simply adding another row to a model leaderboard.

GLM-4.5-Air applies the same hybrid reasoning/agent design philosophy as the larger GLM-4.5 while reducing total and active parameters. Z.ai publishes both BF16 and FP8 versions and positions Air as the efficiency-oriented member of the pair.

From an infrastructure perspective, the key sizing facts are 106B total parameters, 12B/token active parameters and 128K tokens of context. These values should be read together: weight memory, active compute and KV-cache growth describe different resource constraints.

From a governance perspective, the checkpoint is distributed under MIT License. OpenWeightModels records that independently from the fact that the weights are downloadable, because “open weight” is an access classification—not a universal statement about commercial, redistribution or derivative-work rights.

GLM-4.5 Air uses sparse expert routing rather than activating its complete parameter pool for every token. The distinction between 106B total parameters and 12B/token active parameters is central to capacity planning: active parameters influence compute per token, while the complete expert set still affects storage, model loading, sharding and network topology.

This is why OpenWeightModels never maps the active-parameter figure directly to a dense-model hardware class. A sparse model can be computationally efficient per token and still require datacenter-class memory and interconnect to keep all experts available.

Publisher-documented architecture details for this checkpoint include the elements below. These details are more useful for deployment planning than a parameter count alone because attention layout, expert routing, modality encoders and context design can affect throughput and memory independently.

Z.ai documents full-featured BF16 deployment at H100×4 or H200×2 and FP8 at H100×2 or H200×1. For full 128K context it lists BF16 H100×8/H200×4 or FP8 H100×4/H200×2. These concrete profiles make Air unusually easy to capacity-plan.

Real memory use includes model weights, KV cache, activations/buffers, multimodal encoders when applicable, framework overhead and batching. A published “fits on” statement is meaningful only together with precision, context, batch and host/GPU topology.

GLM-4.5 Air is most relevant when the application specifically values efficient reasoning, coding and agent applications with lower infrastructure cost than GLM-4.5. That should be balanced against its hardware class, context behavior, license and modality requirements.

A smaller model can be operationally superior when latency, privacy, device deployment or predictable cost matter more than peak benchmark capability. Conversely, a larger sparse model may justify its complexity when the workload benefits from higher capacity, sophisticated reasoning or agent behavior.

The selection decision should therefore compare at least five dimensions: required task quality, data/control requirements, legal eligibility, serving cost and ecosystem/runtime support. OpenWeightModels exposes these dimensions separately so a model is not selected on benchmark reputation alone.

Last full review: 29 September 2026. Publisher model cards, repositories and license texts are preferred. Runtime claims are attached to the relevant runtime/provider rather than inferred from the base checkpoint.

Where documentation conflicts or a field is ambiguous, the passport uses the more conservative interpretation and explains the discrepancy instead of silently selecting the largest number.