GL

GLM 4.6 REAP 218B A32B Derestricted

GLMGGUF by timowuUpdated 2025-12-07
Download on Hugging Face
Parameters218B
Context198K
Layers92
Architectureglm4moe
Smallest quant131.8 GB
Quick answer

GLM 4.6 REAP 218B A32B Derestricted needs about 135.4 GB of memory at Q4_K_M (a 131.8 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 12.3 GB.

GLM 4.6 REAP 218B A32B Derestricted is a 218B-parameter GLM model in GGUF format, quantized by timowu. Its trained context length is 198K tokens. The repository has 1 quant file, from 131.8 GB (Q4_K_M) to 131.8 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M131.8 GB (9 parts) 135.4 GB
Too big Get file →

What GPU do you need for GLM 4.6 REAP 218B A32B Derestricted?

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 REAP 218B A32B Derestricted quant should you choose?

Q4_K_M is the usual starting point for GLM 4.6 REAP 218B A32B Derestricted: it balances file size and quality well. Here it is a 131.8 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm4moe
Parameters218B (approximate, mixture of experts)
Active parameters32B
Layers92
Trained context202,752 tokens
KV cache (fp16)368 KB per token

Source

Quantized bytimowu
FamilyGLM
Licensemit
Downloads (HF)14
Last updated2025-12-07

Frequently asked questions about GLM 4.6 REAP 218B A32B Derestricted

How much VRAM does GLM 4.6 REAP 218B A32B Derestricted need?

About 135.4 GB at Q4_K_M with an 8K context window. That is the 131.8 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 REAP 218B A32B Derestricted on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 135.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLM 4.6 REAP 218B A32B Derestricted GGUF?

It depends on the quant: Q4_K_M is 131.8 GB.

What context length does GLM 4.6 REAP 218B A32B Derestricted 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 REAP 218B A32B Derestricted GGUF?

The files are on Hugging Face in the timowu/GLM-4.6-REAP-218B-A32B-Derestricted.i1-Q4_K_M-split 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 REAP 218B A32B Derestricted 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 timowu

All by timowu →

More GLM models

All GLM →

Other large models

All large models →