GLM4.6 IQ4 NL needs about 204.8 GB of memory at IQ4_NL (a 201.2 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 12.5 GB.
GLM4.6 IQ4 NL is a 357B-parameter GLM model in GGUF format, quantized by Emanresu. Its trained context length is 198K tokens. The repository has 1 quant file, from 201.2 GB (IQ4_NL) to 201.2 GB (IQ4_NL).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_NL | 201.2 GB (11 parts) | 204.8 GB | Too big | Get file → |
What GPU do you need for GLM4.6 IQ4 NL?
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 GLM4.6 IQ4 NL quant should you choose?
IQ4_NL (201.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM4.6 IQ4 NL
How much VRAM does GLM4.6 IQ4 NL need?
About 204.8 GB at IQ4_NL with an 8K context window. That is the 201.2 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 GLM4.6 IQ4 NL on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 204.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM4.6 IQ4 NL GGUF?
It depends on the quant: IQ4_NL is 201.2 GB.
What context length does GLM4.6 IQ4 NL 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 GLM4.6 IQ4 NL GGUF?
The files are on Hugging Face in the Emanresu/GLM4.6-IQ4_NL-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 GLM4.6 IQ4 NL 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.