Elbaz-GLM-4.7-PRISM needs about 171.9 GB of memory at Q3_K_M (a 168.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 128.6 GB (Q2_K) to 289.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 12.3 GB.
Elbaz-GLM-4.7-PRISM is a 353B-parameter GLM model in GGUF format, quantized by cmckain. Its trained context length is 198K tokens. The repository has 3 quant files, from 128.6 GB (Q2_K) to 289.7 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 128.6 GB | 132.2 GB | Too big | Get file → | |
| Q3_K_M | 168.3 GB | 171.9 GB | Too big | Get file → | |
| Q6_K | 289.7 GB | 293.2 GB | Too big | Get file → |
What GPU do you need for Elbaz-GLM-4.7-PRISM?
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 Elbaz-GLM-4.7-PRISM quant should you choose?
Q3_K_M (168.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K at 128.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Elbaz-GLM-4.7-PRISM
How much VRAM does Elbaz-GLM-4.7-PRISM need?
About 171.9 GB at Q3_K_M with an 8K context window. That is the 168.3 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 Elbaz-GLM-4.7-PRISM on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 132.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Elbaz-GLM-4.7-PRISM GGUF?
It depends on the quant: Q2_K is 128.6 GB, Q3_K_M is 168.3 GB, Q6_K is 289.7 GB.
What context length does Elbaz-GLM-4.7-PRISM 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 Elbaz-GLM-4.7-PRISM GGUF?
The files are on Hugging Face in the cmckain/GLM-4.7-PRISM-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 Elbaz-GLM-4.7-PRISM 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.