GL

GLM 5.3

GLMGGUF by muzzyUpdated 2026-09-29
Download on Hugging Face
Parameters5632B
Context1024K
Layers79
Architectureglm-dsa
Smallest quant181.2 GB
Quick answer

GLM 5.3 needs about 282.8 GB of memory at its main file (a 280.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 181.2 GB to 434.8 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

GLM 5.3 is a 5632B-parameter GLM model in GGUF format, quantized by muzzy. Its trained context length is 1024K tokens. The repository has 5 quant files, from 181.2 GB to 434.8 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—181.2 GB (15 parts) 183.1 GB
Too big Get file →
—220.5 GB (15 parts) 222.4 GB
Too big Get file →
—280.9 GB (15 parts) 282.8 GB
Too big Get file →
—343.4 GB (15 parts) 345.3 GB
Too big Get file →
—434.8 GB (15 parts) 436.8 GB
Too big Get file →

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?

If memory is tight, the smallest file is the first one in the table at 181.2 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm-dsa
Parameters5632B (approximate, mixture of experts)
Layers79
Trained context1,048,576 tokens
KV cache (fp16)168 KB per token

Source

Quantized bymuzzy
FamilyGLM
Base modelzai-org/GLM-5.3
Licensemit
Downloads (HF)252
Last updated2026-09-29

Frequently asked questions about GLM 5.3

How much VRAM does GLM 5.3 need?

About 282.8 GB at its main file with an 8K context window. That is the 280.9 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 5.3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 183.1 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: file is 181.2 GB, file is 220.5 GB, file is 280.9 GB, file is 343.4 GB, file is 434.8 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 muzzy/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 mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of GLM-5.3

Similar models

Browse all →

More from muzzy

All by muzzy →

More GLM models

All GLM →

Other large models

All large models →