GL

GLM 5.2 Safetensors

GLMGGUF by batiaiUpdated 2026-06-22
Download on Hugging Face
Parameters753B
Context1024K
Layers79
Architectureglm-dsa
Smallest quant230.0 GB
Quick answer

GLM 5.2 Safetensors needs about 294.6 GB of memory at IQ3_XXS (a 292.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 230.0 GB (IQ2_XS) to 360.9 GB (Q3_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

GLM 5.2 Safetensors is a 753B-parameter GLM model in GGUF format, quantized by batiai. Its trained context length is 1024K tokens. The repository has 3 quant files, from 230.0 GB (IQ2_XS) to 360.9 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XS230.0 GB (5 parts) 231.9 GB
Too big Get file →
IQ3_XXS292.7 GB (7 parts) 294.6 GB
Too big Get file →
Q3_K_M360.9 GB (8 parts) 362.8 GB
Too big Get file →

What GPU do you need for GLM 5.2 Safetensors?

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 5.2 Safetensors quant should you choose?

IQ3_XXS (292.7 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ2_XS at 230.0 GB, with the quality trade-offs that come with fewer bits. 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
Parameters753B (approximate, mixture of experts)
Layers79
Trained context1,048,576 tokens
KV cache (fp16)168 KB per token

Source

Quantized bybatiai
FamilyGLM
Base modelzai-org/GLM-5.2
Licenseother
Downloads (HF)116
Last updated2026-06-22

Frequently asked questions about GLM 5.2 Safetensors

How much VRAM does GLM 5.2 Safetensors need?

About 294.6 GB at IQ3_XXS with an 8K context window. That is the 292.7 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 5.2 Safetensors on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 231.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 5.2 Safetensors GGUF?

It depends on the quant: IQ2_XS is 230.0 GB, IQ3_XXS is 292.7 GB, Q3_K_M is 360.9 GB.

What context length does GLM 5.2 Safetensors 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 5.2 Safetensors GGUF?

The files are on Hugging Face in the batiai/GLM-5.2-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 5.2 Safetensors use?

Hugging Face lists the license as other. 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-5.2

Similar models

Browse all →

More from batiai

All by batiai →

More GLM models

All GLM →

Other large models

All large models →