GL

glm 5.3

GLMGGUF by antirezUpdated 2026-08-31
Download on Hugging Face
Parameters754B
Context1024K
Layers79
Architectureglm-dsa
Smallest quant211.1 GB
Quick answer

glm 5.3 needs about 213.0 GB of memory at IQ2_XXS (a 211.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

GLM 5.3 – 800 Billion‑parameter LLM in a single GGUF file

GLM 5.3 is an 800 billion‑parameter language model based on the glm‑dsa architecture. The model is released as a single GGUF file quantized with IQ2_XXS, providing a compact representation for local inference.

Good at

  • Large context handling up to 1 048 576 tokens
  • High‑capacity language modeling
  • Efficient inference with IQ2_XXS quantization

Limits

  • Requires ~213 GB VRAM at 8 k context
  • No vision or multimodal support
  • License is glm‑5.3, usage restrictions apply

Best for

  • Research requiring massive context windows
  • Testing extreme‑scale language modeling
  • Benchmarking GGUF inference performance

Who it’s for. Researchers and developers needing a very large language model for local inference. The single‑file GGUF format allows deployment on systems with sufficient GPU memory, but the size limits practical use to high‑end workstations or servers.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS211.1 GB 213.0 GB
Too big Get file →

The only available quant is IQ2_XXS, with a file size of 211 GB and an estimated VRAM requirement of 213 GB at 8 k context. This quant is suitable for users with large GPU memory budgets; otherwise the model cannot be run locally.

What GPU do you need for glm 5.3?

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.

Which glm 5.3 quant should you choose?

IQ2_XXS (211.1 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm-dsa
Parameters754B (approximate, mixture of experts)
Layers79
Trained context1,048,576 tokens
KV cache (fp16)168 KB per token

Source

Quantized byantirez
FamilyGLM
Licenseglm-5.3
Downloads (HF)23,856
Last updated2026-08-31

Frequently asked questions about glm 5.3

How much VRAM does glm 5.3 need?

About 213.0 GB at IQ2_XXS with an 8K context window. That is the 211.1 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 5.3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 213.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of glm 5.3 GGUF?

It depends on the quant: IQ2_XXS is 211.1 GB.

What context length does glm 5.3 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download glm 5.3 GGUF?

The files are on Hugging Face in the antirez/glm-5.3-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 5.3 use?

Hugging Face lists the license as glm-5.3. 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 5.3 on a GPU with 8 GB VRAM?

No. The IQ2_XXS quant requires about 213 GB VRAM at 8 k context, far beyond 8 GB.

Is GLM 5.3 a mixture of experts model?

No, the active parameters for MOE are null; it is a standard large‑parameter model.

Similar models

Browse all →

More from antirez

All by antirez →

More GLM models

All GLM →

Other large models

All large models →