GL

GLM 4.5 Air REAP 82B A12B MXFP4 MOE

GLMGGUF by noctrexUpdated 2025-10-28
Download on Hugging Face
Parameters85B
Context128K
Layers47
Architectureglm4moe
Smallest quant49.8 GB
Quick answer

GLM 4.5 Air REAP 82B A12B MXFP4 MOE needs about 51.9 GB of memory at MXFP4_MOE (a 49.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 49.8 GB (MXFP4_MOE) to 49.8 GB (MXFP4_MOE). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.

GLM 4.5 Air REAP 82B A12B MXFP4 MOE is a 85B-parameter GLM model in GGUF format, quantized by noctrex. Its trained context length is 128K tokens. The repository has 2 quant files, from 49.8 GB (MXFP4_MOE) to 49.8 GB (MXFP4_MOE).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE49.8 GB (3 parts) 51.9 GB
Too big Get file →
MXFP4_MOE49.8 GB (3 parts) 51.9 GB
Too big Get file →

What GPU do you need for GLM 4.5 Air REAP 82B A12B 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 4.5 Air REAP 82B A12B MXFP4 MOE quant should you choose?

MXFP4_MOE (49.8 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
Parameters85B (approximate, mixture of experts)
Active parameters12B
Layers47
Trained context131,072 tokens
KV cache (fp16)188 KB per token

Source

Quantized bynoctrex
FamilyGLM
Licensemit
Downloads (HF)55
Last updated2025-10-28

Frequently asked questions about GLM 4.5 Air REAP 82B A12B MXFP4 MOE

How much VRAM does GLM 4.5 Air REAP 82B A12B MXFP4 MOE need?

About 51.9 GB at MXFP4_MOE with an 8K context window. That is the 49.8 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 4.5 Air REAP 82B A12B MXFP4 MOE on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 51.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 4.5 Air REAP 82B A12B MXFP4 MOE GGUF?

It depends on the quant: MXFP4_MOE is 49.8 GB, MXFP4_MOE is 49.8 GB.

What context length does GLM 4.5 Air REAP 82B A12B MXFP4 MOE 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 GLM 4.5 Air REAP 82B A12B MXFP4 MOE GGUF?

The files are on Hugging Face in the noctrex/GLM-4.5-Air-REAP-82B-A12B-MXFP4_MOE-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 4.5 Air REAP 82B A12B 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-4.5-Air-REAP-82B-A12B

Similar models

Browse all →

More from noctrex

All by noctrex →

More GLM models

All GLM →

Other large models

All large models →