GL

GLM 5.2 MXFP4 MOE Q8 0

GLMGGUF by MaliAirUpdated 2026-07-26
Download on Hugging Face
Parameters754B
Context1024K
Layers79
Architectureglm-dsa
Smallest quant410.6 GB
Quick answer

GLM 5.2 MXFP4 MOE Q8 0 needs about 412.5 GB of memory at MXFP4 (a 410.6 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 5.2 MXFP4 MOE Q8 0 is a 754B-parameter GLM model in GGUF format, quantized by MaliAir. Its trained context length is 1024K tokens. The repository has 1 quant file, from 410.6 GB (MXFP4) to 410.6 GB (MXFP4).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4410.6 GB (77 parts) 412.5 GB
Too big Get file →

What GPU do you need for GLM 5.2 MXFP4 MOE Q8 0?

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 MXFP4 MOE Q8 0 quant should you choose?

MXFP4 (410.6 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

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 byMaliAir
FamilyGLM
Licenseapache-2.0
Downloads (HF)25
Last updated2026-07-26

Frequently asked questions about GLM 5.2 MXFP4 MOE Q8 0

How much VRAM does GLM 5.2 MXFP4 MOE Q8 0 need?

About 412.5 GB at MXFP4 with an 8K context window. That is the 410.6 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 MXFP4 MOE Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 412.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 5.2 MXFP4 MOE Q8 0 GGUF?

It depends on the quant: MXFP4 is 410.6 GB.

What context length does GLM 5.2 MXFP4 MOE Q8 0 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 MXFP4 MOE Q8 0 GGUF?

The files are on Hugging Face in the MaliAir/GLM-5.2-MXFP4-MOE-Q8_0-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 MXFP4 MOE Q8 0 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from MaliAir

All by MaliAir →

More GLM models

All GLM →

Other large models

All large models →