GLM 4.7 PRISM Unsloth needs about 136.8 GB of memory at Q2_K_XL (a 133.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 82.7 GB (TQ1_0) to 388.9 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 12.3 GB.
GLM 4.7 PRISM Unsloth is a 353B-parameter GLM model in GGUF format, quantized by AliceThirty. Its trained context length is 198K tokens. The repository has 8 quant files, from 82.7 GB (TQ1_0) to 388.9 GB (Q8_K_XL).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 82.7 GB | 86.2 GB | Too big | Get file → | |
| IQ2_XXS | 92.2 GB (2 parts) | 95.7 GB | Too big | Get file → | |
| IQ2_XXS | 113.9 GB (3 parts) | 117.5 GB | Too big | Get file → | |
| Q2_K_XL | 133.2 GB (3 parts) | 136.8 GB | Too big | Get file → | |
| Q4_K_XL | 201.4 GB (5 parts) | 205.0 GB | Too big | Get file → | |
| Q5_K_XL | 250.4 GB (6 parts) | 254.0 GB | Too big | Get file → | |
| Q6_K_XL | 296.5 GB (6 parts) | 300.1 GB | Too big | Get file → | |
| Q8_K_XL | 388.9 GB (8 parts) | 392.5 GB | Too big | Get file → |
What GPU do you need for GLM 4.7 PRISM Unsloth?
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 4.7 PRISM Unsloth quant should you choose?
Q2_K_XL (133.2 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is TQ1_0 at 82.7 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM 4.7 PRISM Unsloth
How much VRAM does GLM 4.7 PRISM Unsloth need?
About 136.8 GB at Q2_K_XL with an 8K context window. That is the 133.2 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 GLM 4.7 PRISM Unsloth on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 86.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM 4.7 PRISM Unsloth GGUF?
It depends on the quant: TQ1_0 is 82.7 GB, IQ2_XXS is 92.2 GB, IQ2_XXS is 113.9 GB, Q2_K_XL is 133.2 GB, Q4_K_XL is 201.4 GB, Q5_K_XL is 250.4 GB and 2 more.
What context length does GLM 4.7 PRISM Unsloth 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 GLM 4.7 PRISM Unsloth GGUF?
The files are on Hugging Face in the AliceThirty/GLM-4.7-PRISM-Unsloth-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 4.7 PRISM Unsloth 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.