GLM 4.6 Derestricted needs about 143.3 GB of memory at Q8_0 (a 139.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 139.7 GB (Q8_0) to 163.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.5 GB.
GLM 4.6 Derestricted is a 357B-parameter GLM model in GGUF format, quantized by ddh0. Its trained context length is 198K tokens. The repository has 2 quant files, from 139.7 GB (Q8_0) to 163.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 139.7 GB (4 parts) | 143.3 GB | Too big | Get file → | |
| Q8_0 | 163.4 GB (5 parts) | 167.1 GB | Too big | Get file → |
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: 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 Derestricted quant should you choose?
Q8_0 (139.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM 4.6 Derestricted
How much VRAM does GLM 4.6 Derestricted need?
About 143.3 GB at Q8_0 with an 8K context window. That is the 139.7 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?
Not at an 8K context. The smallest file needs about 143.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM 4.6 Derestricted GGUF?
It depends on the quant: Q8_0 is 139.7 GB, Q8_0 is 163.4 GB.
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 ddh0/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.