GL

GLM 4.6 MXFP4 MOE

GLMGGUF by sm54Updated 2025-10-01
Download on Hugging Face
Parameters357B
Context198K
Layers93
Architectureglm4moe
Smallest quant198.8 GB
Quick answer

GLM 4.6 MXFP4 MOE needs about 202.5 GB of memory at MXFP4_MOE (a 198.8 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 12.5 GB.

GLM 4.6 MXFP4 MOE is a 357B-parameter GLM model in GGUF format, quantized by sm54. Its trained context length is 198K tokens. The repository has 1 quant file, from 198.8 GB (MXFP4_MOE) to 198.8 GB (MXFP4_MOE).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE198.8 GB (5 parts) 202.5 GB
Too big Get file →

What GPU do you need for GLM 4.6 MXFP4 MOE?

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 4.6 MXFP4 MOE quant should you choose?

MXFP4_MOE (198.8 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

Architectureglm4moe
Parameters357B (approximate, mixture of experts)
Layers93
Trained context202,752 tokens
KV cache (fp16)372 KB per token

Source

Quantized bysm54
FamilyGLM
Base modelzai-org/GLM-4.6
Licensemit
Downloads (HF)11
Last updated2025-10-01

Frequently asked questions about GLM 4.6 MXFP4 MOE

How much VRAM does GLM 4.6 MXFP4 MOE need?

About 202.5 GB at MXFP4_MOE with an 8K context window. That is the 198.8 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 4.6 MXFP4 MOE on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 202.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 4.6 MXFP4 MOE GGUF?

It depends on the quant: MXFP4_MOE is 198.8 GB.

What context length does GLM 4.6 MXFP4 MOE support?

The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 3.1 GB at 8K and 12.5 GB at 32K.

Where can I download GLM 4.6 MXFP4 MOE GGUF?

The files are on Hugging Face in the sm54/GLM-4.6-MXFP4_MOE 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 4.6 MXFP4 MOE 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-4.6

Similar models

Browse all →

More from sm54

All by sm54 →

More GLM models

All GLM →

Other large models

All large models →