zai-org/GLM-4.5-Air

zai-org/GLM-4.5-Air is listed on Hugging Face as a text-generation model. This page records the public repository snapshot a24ceef6ce4f3536971efe9b778bdaa1bab18daa; verify the listed revision, licence, and runtime support before using it.

Updated

Computraq is preparing for launch. These guides explain readiness and the proposed framework; they do not establish a live service, integration or partnership.

Identity and access

The publisher record identifies this repository as zai-org/GLM-4.5-Air. Its current public snapshot is a24ceef6ce4f3536971efe9b778bdaa1bab18daa. Access is public repository; review the applicable licence and publisher terms; the recorded licence label is mit. A public repository or gated download does not establish permission for every use.

Configuration facts

The pinned configuration reports model type glm4_moe and architecture Glm4MoeForCausalLM. The model hub tags it for text-generation; these labels describe repository metadata and do not establish benchmark performance.

  • head_dim: 128
  • hidden_size: 4096
  • intermediate_size: 10944
  • max_position_embeddings: 131072
  • num_attention_heads: 96
  • n_routed_experts: 128
  • num_experts_per_tok: 8
  • num_hidden_layers: 46
  • num_key_value_heads: 8
  • rms_norm_eps: 1e-05
  • rope_theta: 1000000
  • torch_dtype: bfloat16
  • vocab_size: 151552

Model-specific qualification

This configuration or publisher metadata marks the model as a mixture of experts. Confirm whether the serving runtime supports its routing layers, and distinguish total parameters from parameters active per token; no active count is inferred here unless the publisher explicitly states one.

Weight-memory planning

This guide does not retain an independently verified logical parameter count, so it omits a numeric weight-memory estimate. If a count is verified for this exact repository revision, use parameter count × bytes per parameter for a weights-only floor; then account separately for KV cache, context, activations, runtime, and concurrency.

Revision and reproducibility

The metadata and configuration are pinned to revision a24ceef6ce4f3536971efe9b778bdaa1bab18daa. Pin this commit when reproducing an evaluation. Repository branches can change, and this source check does not validate the model weights themselves.

Published record

  • Task: text-generation
  • Model type: glm4_moe
  • Architecture: Glm4MoeForCausalLM
  • Licence label: mit
  • Access: public repository; review the applicable licence and publisher terms
  • Revision: a24ceef6ce4f3536971efe9b778bdaa1bab18daa

Sources and verification