GL

GLM 4.5 Air

GLMGGUF by auRose94Updated 2026-10-26
Download on Hugging Face
Parameters78.8B
Context128K
Layers47
Architectureglm4moe
Smallest quant78.9 GB
Quick answer

GLM 4.5 Air needs about 81.0 GB of memory at its main file (a 78.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 78.9 GB to 78.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.

GLM 4.5 Air – a compact 78.89 GB GGUF model for intelligent agents

GLM 4.5 Air is a 78.89 GB GGUF model based on the GLM‑4.5‑Air architecture. It contains 78.8 billion parameters and is designed for reasoning, coding, and agent tasks. The model is released under the MIT license and can be used commercially.

Good at

  • Hybrid reasoning with thinking and non‑thinking modes
  • Efficient agent‑centric workloads
  • Large‑context support up to 131072 tokens

Limits

  • Requires ~81 GB VRAM at 8k context
  • No vision or audio capabilities
  • No quantization options listed beyond the base GGUF

Best for

  • Building chat‑based intelligent agents
  • Complex reasoning workflows
  • Code generation tasks

Who it’s for. Developers and researchers building intelligent agent applications who need a large‑context, reasoning‑capable model with an open‑source MIT license. The model is suitable for commercial and secondary development use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—78.9 GB 81.0 GB
Too big Get file →
—78.9 GB 81.0 GB
Too big Get file →

The available GGUF files are both 78.89 GB and estimate 81 GB of VRAM at 8k context. For systems with 8 GB VRAM or less, the model cannot be loaded. If a larger GPU is available, the base GGUF can be used directly; no additional quantization is provided.

What GPU do you need for GLM 4.5 Air?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Specifications

Architecture from the GGUF header

Architectureglm4moe
Parameters78.8B (approximate, mixture of experts)
Layers47
Trained context131,072 tokens
KV cache (fp16)188 KB per token

Source

Quantized byauRose94
FamilyGLM
Licensemit
Downloads (HF)1,084
Last updated2026-10-26

Frequently asked questions about GLM 4.5 Air

How much VRAM does GLM 4.5 Air need?

About 81.0 GB at its main file with an 8K context window. That is the 78.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run GLM 4.5 Air on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 81.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 4.5 Air GGUF?

It depends on the quant: file is 78.9 GB, file is 78.9 GB.

What context length does GLM 4.5 Air support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.3 GB at 32K.

Where can I download GLM 4.5 Air GGUF?

The files are on Hugging Face in the auRose94/GLM-4.5-Air-ninths-k63-e99-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does GLM 4.5 Air use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run GLM 4.5 Air on 8 GB VRAM?

No. The model estimates 81 GB of VRAM at 8k context, so 8 GB is insufficient.

Does GLM 4.5 Air support vision or audio?

No. The model only provides text‑based reasoning and agent capabilities.

Other GGUFs of GLM-4.5-Air

Similar models

Browse all →

More from auRose94

All by auRose94 →

More GLM models

All GLM →

Other large models

All large models →