GLM-4.5

Checkpoint identity

Official identifier

zai-org/GLM-4.5Z.ai GLM-4.5 model card (external source) · GLM-4.5 checkpoint configuration (external source) · GLM-4.5 code repository license (external source)

Architecture

Mixture of experts; hybrid thinking and non-thinking text modelZ.ai GLM-4.5 model card (external source) · GLM-4.5 checkpoint configuration (external source) · GLM-4.5 code repository license (external source)

Total parameters

355 billionPublished rounded counts; total stored weights determine the preliminary footprint, including all MoE experts.Z.ai GLM-4.5 model card (external source) · GLM-4.5 checkpoint configuration (external source) · GLM-4.5 code repository license (external source)

Active parameters

32 billion per tokenActive parameters are a compute-related count, not the model's full stored weight count.Z.ai GLM-4.5 model card (external source) · GLM-4.5 checkpoint configuration (external source) · GLM-4.5 code repository license (external source)

Modalities

text-input, text-outputZ.ai GLM-4.5 model card (external source) · GLM-4.5 checkpoint configuration (external source) · GLM-4.5 code repository license (external source)

Context

131,072 tokensNative configuration where directly verified. Extensions, advertised K-labels and configuration differences are preserved in the notes below.Z.ai GLM-4.5 model card (external source) · GLM-4.5 checkpoint configuration (external source) · GLM-4.5 code repository license (external source)

Release date

Exact release date not independently established in the reviewed artifactsZ.ai GLM-4.5 model card (external source) · GLM-4.5 checkpoint configuration (external source) · GLM-4.5 code repository license (external source)

Download access

Public checkpoint referenceZ.ai GLM-4.5 model card (external source) · GLM-4.5 checkpoint configuration (external source) · GLM-4.5 code repository license (external source)

License

MIT (model weights)The checkpoint card identifies the weights as MIT and describes commercial use. The separate code repository has an Apache 2.0 LICENSE. Check the terms for each downloaded artifact; this description is not a deployment clearance.Z.ai GLM-4.5 model card (external source) · GLM-4.5 checkpoint configuration (external source) · GLM-4.5 code repository license (external source)

Theoretical weight-memory footprint

Using the publisher's approximately 355 billion total parameters at 16 bits per parameter gives 710 GB (661.2 GiB) of nominal weights.

This estimate excludes KV cache, activations, quantization metadata, non-weight buffers and serving overhead. It is not a tested GPU fit. MoE routing activates only part of the network per token while the complete expert weights still need storage.

Quantization

This checkpoint is BF16; the publisher also lists a separate FP8 checkpoint. FP8 needs compatible hardware and runtime kernels.

Serving considerations

• Parameter counts are the publisher's rounded, approximate counts; active parameters do not represent the full weight memory footprint.
• The config specifies 131,072 positions; the card describes this as 128K context. Long context and batching increase cache memory requirements.
• Framework links are documentation starting points. Aguasto has not evaluated or deployed this checkpoint, and no throughput or GPU-fit result is claimed.

Framework documentation

These are third-party documentation starting points. Support depends on the exact checkpoint, runtime version and hardware.