GL

glm 4.6 268b

GLMGGUF by rsarwarUpdated 2025-12-06
Download on Hugging Face
Parameters269B
Context198K
Layers92
Architectureglm4moe
Smallest quant109.6 GB
Quick answer

glm 4.6 268b needs about 113.2 GB of memory at IQ3_XS (a 109.6 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 12.3 GB.

glm 4.6 268b is a 269B-parameter GLM model in GGUF format, quantized by rsarwar. Its trained context length is 198K tokens. The repository has 1 quant file, from 109.6 GB (IQ3_XS) to 109.6 GB (IQ3_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XS109.6 GB 113.2 GB
Too big Get file →

What GPU do you need for glm 4.6 268b?

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 268b quant should you choose?

IQ3_XS (109.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm4moe
Parameters269B (approximate, mixture of experts)
Layers92
Trained context202,752 tokens
KV cache (fp16)368 KB per token

Source

Quantized byrsarwar
FamilyGLM
Licensemit
Downloads (HF)14
Last updated2025-12-06

Frequently asked questions about glm 4.6 268b

How much VRAM does glm 4.6 268b need?

About 113.2 GB at IQ3_XS with an 8K context window. That is the 109.6 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 4.6 268b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 113.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of glm 4.6 268b GGUF?

It depends on the quant: IQ3_XS is 109.6 GB.

What context length does glm 4.6 268b 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 12.3 GB at 32K.

Where can I download glm 4.6 268b GGUF?

The files are on Hugging Face in the rsarwar/glm-4.6-268b 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 268b 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.

Similar models

Browse all →

More GLM models

All GLM →

Other large models

All large models →