GLM 4.7 Flash PRISM needs about 19.5 GB of memory at Q4_K_M (a 18.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 14.4 GB (Q3_K_M) to 59.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
GLM 4.7 Flash PRISM is a 29.9B-parameter GLM model in GGUF format, quantized by Ex0bit. Its trained context length is 198K tokens. The repository has 5 quant files, from 14.4 GB (Q3_K_M) to 59.9 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 14.4 GB | 15.7 GB | Too big | Get file → | |
| IQ4_NL | 17.0 GB | 18.3 GB | Too big | Get file → | |
| Q4_K_M | 18.1 GB | 19.5 GB | Too big | Get file → | |
| Q8_0 | 31.8 GB | 33.2 GB | Too big | Get file → | |
| BF16 | 59.9 GB | 61.2 GB | Too big | Get file → |
What GPU do you need for GLM 4.7 Flash 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: the best quant that fits is Q3_K_M (14.4 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (18.1 GB file, about 19.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (18.1 GB file, about 19.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (31.8 GB file, about 33.2 GB in use).
Which GLM 4.7 Flash PRISM quant should you choose?
Q4_K_M is the usual starting point for GLM 4.7 Flash PRISM: it balances file size and quality well. Here it is a 18.1 GB file.
The Q8_0 file is 31.8 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q3_K_M at 14.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM 4.7 Flash PRISM
How much VRAM does GLM 4.7 Flash PRISM need?
About 19.5 GB at Q4_K_M with an 8K context window. That is the 18.1 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 Flash PRISM on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM 4.7 Flash PRISM GGUF?
It depends on the quant: Q3_K_M is 14.4 GB, IQ4_NL is 17.0 GB, Q4_K_M is 18.1 GB, Q8_0 is 31.8 GB, BF16 is 59.9 GB.
What context length does GLM 4.7 Flash 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 0.8 GB at 8K and 3.4 GB at 32K.
Where can I download GLM 4.7 Flash PRISM GGUF?
The files are on Hugging Face in the Ex0bit/GLM-4.7-Flash-PRISM 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 Flash PRISM use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.