GL

TheDrummer GLM Air A12B 80E

GLMGGUF by blascotobascoUpdated 2026-01-16
Download on Hugging Face
Parameters72.3B
Context128K
Layers47
Architectureglm4moe
Smallest quant47.5 GB
Quick answer

TheDrummer GLM Air A12B 80E needs about 49.5 GB of memory at Q4_K_M (a 47.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 47.5 GB (Q4_K_M) to 144.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.

TheDrummer GLM Air A12B 80E is a 72.3B-parameter GLM model in GGUF format, quantized by blascotobasco. Its trained context length is 128K tokens. The repository has 2 quant files, from 47.5 GB (Q4_K_M) to 144.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M47.5 GB 49.5 GB
Too big Get file →
F16144.6 GB 146.6 GB
Too big Get file →

What GPU do you need for TheDrummer GLM Air A12B 80E?

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 TheDrummer GLM Air A12B 80E quant should you choose?

Q4_K_M is the usual starting point for TheDrummer GLM Air A12B 80E: it balances file size and quality well. Here it is a 47.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm4moe
Parameters72.3B (approximate, mixture of experts)
Active parameters12B
Layers47
Trained context131,072 tokens
KV cache (fp16)188 KB per token

Source

Quantized byblascotobasco
FamilyGLM
Downloads (HF)38
Last updated2026-01-16

Frequently asked questions about TheDrummer GLM Air A12B 80E

How much VRAM does TheDrummer GLM Air A12B 80E need?

About 49.5 GB at Q4_K_M with an 8K context window. That is the 47.5 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 TheDrummer GLM Air A12B 80E on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 49.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of TheDrummer GLM Air A12B 80E GGUF?

It depends on the quant: Q4_K_M is 47.5 GB, F16 is 144.6 GB.

What context length does TheDrummer GLM Air A12B 80E support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 TheDrummer GLM Air A12B 80E GGUF?

The files are on Hugging Face in the blascotobasco/TheDrummer-GLM-Air-A12B-80E-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from blascotobasco

All by blascotobasco →

More GLM models

All GLM →

Other large models

All large models →