GLM 4.6 128GB RAM IK needs about 137.4 GB of memory at its main file (a 133.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 132.3 GB to 136.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 12.5 GB.
GLM 4.6 128GB RAM IK is a 357B-parameter GLM model in GGUF format, quantized by Downtown-Case. Its trained context length is 198K tokens. The repository has 3 quant files, from 132.3 GB to 136.2 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 132.3 GB (3 parts) | 136.0 GB | Too big | Get file → | |
| — | 133.7 GB (3 parts) | 137.4 GB | Too big | Get file → | |
| — | 136.2 GB (3 parts) | 139.8 GB | Too big | Get file → |
What GPU do you need for GLM 4.6 128GB RAM IK?
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 128GB RAM IK quant should you choose?
If memory is tight, the smallest file is the first one in the table at 132.3 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
Source
Frequently asked questions about GLM 4.6 128GB RAM IK
How much VRAM does GLM 4.6 128GB RAM IK need?
About 137.4 GB at its main file with an 8K context window. That is the 133.7 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 128GB RAM IK on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 136.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM 4.6 128GB RAM IK GGUF?
It depends on the quant: file is 132.3 GB, file is 133.7 GB, file is 136.2 GB.
What context length does GLM 4.6 128GB RAM IK 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 128GB RAM IK GGUF?
The files are on Hugging Face in the Downtown-Case/GLM-4.6-128GB-RAM-IK-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 128GB RAM IK 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.