GL

GLM Air Q4KM Yarn 65k

GLMGGUF by ColumbidaeUpdated 2025-09-04
Download on Hugging Face
Parameters120B
Context64K
Layers47
Architectureglm4moe
Smallest quant39.8 GB
Quick answer

GLM Air Q4KM Yarn 65k needs about 41.9 GB of memory at Q4_K_M (a 39.8 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 39.8 GB (Q4_K_M) to 73.5 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.

GLM Air Q4KM Yarn 65k is a 120B-parameter GLM model in GGUF format, quantized by Columbidae. Its trained context length is 64K tokens. The repository has 2 quant files, from 39.8 GB (Q4_K_M) to 73.5 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M39.8 GB 41.9 GB
Too big Get file →
Q4_K_M73.5 GB (2 parts) 75.6 GB
Too big Get file →

What GPU do you need for GLM Air Q4KM Yarn 65k?

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: the best quant that fits is Q4_K_M (39.8 GB file, about 41.9 GB in use).

Which GLM Air Q4KM Yarn 65k quant should you choose?

Q4_K_M is the usual starting point for GLM Air Q4KM Yarn 65k: it balances file size and quality well. Here it is a 39.8 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm4moe
Parameters120B (approximate, mixture of experts)
Layers47
Trained context65,536 tokens
KV cache (fp16)188 KB per token

Source

Quantized byColumbidae
FamilyGLM
Licensemit
Downloads (HF)9
Last updated2025-09-04

Frequently asked questions about GLM Air Q4KM Yarn 65k

How much VRAM does GLM Air Q4KM Yarn 65k need?

About 41.9 GB at Q4_K_M with an 8K context window. That is the 39.8 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 Air Q4KM Yarn 65k on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 41.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM Air Q4KM Yarn 65k GGUF?

It depends on the quant: Q4_K_M is 39.8 GB, Q4_K_M is 73.5 GB.

What context length does GLM Air Q4KM Yarn 65k support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.3 GB at 32K.

Where can I download GLM Air Q4KM Yarn 65k GGUF?

The files are on Hugging Face in the Columbidae/GLM-Air-Q4KM-Yarn-65k 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 Air Q4KM Yarn 65k 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 from Columbidae

All by Columbidae →

More GLM models

All GLM →

Other large models

All large models →