GL

GLM 4.6 Derestricted

GLMGGUF by bartowskiUpdated 2025-12-11
Download on Hugging Face
Parameters357B
Context198K
Layers93
Architectureglm4moe
Smallest quant0.7 GB
Quick answer

GLM 4.6 Derestricted needs about 221.3 GB of memory at Q4_K_M (a 217.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 26 quants, from 0.7 GB to 379.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.5 GB.

GLM 4.6 Derestricted – a large, uncensored language model

GLM 4.6 Derestricted is a 357‑billion‑parameter model that removes refusal behaviors while keeping reasoning performance. It is built on the glm4moe architecture and supports a 202,752‑token context window. The model is released under the MIT license.

Good at

  • Large context reasoning
  • Uncensored text generation
  • High‑capacity language tasks

Limits

  • No vision support
  • Requires large VRAM for full precision
  • No official benchmark scores

Best for

  • Chatbots needing extended context
  • Research on uncensored language models
  • Long‑form content generation

Who it’s for. Developers and researchers who need a large, uncensored language model with a 202,752‑token context. The model is suitable for applications that can accommodate its memory footprint and do not require vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.7 GB 4.3 GB
Fits Get file →
IQ1_S76.3 GB (2 parts) 79.9 GB
Too big Get file →
IQ1_M79.6 GB (2 parts) 83.2 GB
Too big Get file →
IQ2_XXS88.3 GB (3 parts) 91.9 GB
Too big Get file →
IQ2_XS101.0 GB (3 parts) 104.7 GB
Too big Get file →
IQ2_S101.9 GB (3 parts) 105.5 GB
Too big Get file →
IQ2_M115.0 GB (3 parts) 118.7 GB
Too big Get file →
Q2_K127.2 GB (4 parts) 130.9 GB
Too big Get file →
Q2_K_L128.0 GB (4 parts) 131.6 GB
Too big Get file →
IQ3_XXS142.4 GB (4 parts) 146.1 GB
Too big Get file →
IQ3_XS148.2 GB (4 parts) 151.8 GB
Too big Get file →
Q3_K_S156.7 GB (4 parts) 160.3 GB
Too big Get file →
IQ3_M164.3 GB (5 parts) 167.9 GB
Too big Get file →
Q3_K_M164.3 GB (5 parts) 167.9 GB
Too big Get file →
Q3_K_L169.9 GB (5 parts) 173.5 GB
Too big Get file →
Q3_K_XL170.6 GB (5 parts) 174.2 GB
Too big Get file →
IQ4_XS192.0 GB (5 parts) 195.6 GB
Too big Get file →
IQ4_NL202.9 GB (6 parts) 206.5 GB
Too big Get file →
Q4_0205.6 GB (6 parts) 209.2 GB
Too big Get file →
Q4_K_S209.9 GB (6 parts) 213.5 GB
Too big Get file →
Q4_K_M217.7 GB (6 parts) 221.3 GB
Too big Get file →
Q4_1224.2 GB (6 parts) 227.8 GB
Too big Get file →
Q5_K_S246.4 GB (7 parts) 250.0 GB
Too big Get file →
Q5_K_M254.2 GB (7 parts) 257.8 GB
Too big Get file →
Q6_K293.6 GB (8 parts) 297.2 GB
Too big Get file →
Q8_0379.3 GB (10 parts) 382.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (76.31 GB file, 79.9 GB memory at 8 k context). For 16 GB VRAM, IQ2_XS (101.04 GB file, 104.7 GB memory) or Q2_K (127.25 GB file, 130.9 GB memory). For 24 GB VRAM, Q4_K_M (217.65 GB file, 221.3 GB memory) or Q5_K_M (254.21 GB file, 257.8 GB memory).

What GPU do you need for GLM 4.6 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: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).

Which GLM 4.6 Derestricted quant should you choose?

Q4_K_M is the usual starting point for GLM 4.6 Derestricted: it balances file size and quality well. Here it is a 217.7 GB file.

The Q8_0 file is 379.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.7 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm4moe
Parameters357B (approximate, mixture of experts)
Layers93
Trained context202,752 tokens
KV cache (fp16)372 KB per token

Source

Quantized bybartowski
FamilyGLM
Licensemit
Downloads (HF)1,417
Last updated2025-12-11

Frequently asked questions about GLM 4.6 Derestricted

How much VRAM does GLM 4.6 Derestricted need?

About 221.3 GB at Q4_K_M with an 8K context window. That is the 217.7 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 Derestricted on an 8 GB GPU?

Yes, with the smaller files: the 0.7 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GLM 4.6 Derestricted GGUF?

It depends on the quant: file is 0.7 GB, IQ1_S is 76.3 GB, IQ1_M is 79.6 GB, IQ2_XXS is 88.3 GB, IQ2_XS is 101.0 GB, IQ2_S is 101.9 GB and 20 more.

What context length does GLM 4.6 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 12.5 GB at 32K.

Where can I download GLM 4.6 Derestricted GGUF?

The files are on Hugging Face in the bartowski/ArliAI_GLM-4.6-Derestricted-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 4.6 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.

Can I run GLM 4.6 Derestricted on 8 GB VRAM?

Only the IQ1_S quant (76.31 GB file, 79.9 GB memory at 8 k context) fits within an 8 GB VRAM budget, but it still requires significant RAM.

Does the model support vision tasks?

No, GLM 4.6 Derestricted does not include vision capabilities.

What license does the model use?

The model is released under the MIT license.

Other GGUFs of GLM-4.6-Derestricted-v3

Similar models

Browse all →

More from bartowski

All by bartowski →

More GLM models

All GLM →

Other large models

All large models →