GLM 4.7 Flash Derestricted 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 11 quants, from 11.0 GB (Q2_K) to 31.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
30B GLM-4.7 Flash Derestricted in GGUF format
GLM-4.7 Flash Derestricted is a 30 billion‑parameter model based on the deepseek2 architecture. It is uncensored using Norm‑Preserving Biprojected Abliteration. The model supports up to 202 752 context tokens and is released under the MIT license.
Good at
- Large context handling
- Uncensored text generation
- High parameter count
Limits
- No vision support
- Requires significant VRAM for larger quants
- No explicit language support list
Best for
- Research on large‑context LLMs
- Developing custom applications needing uncensored output
- Benchmarking quantization effects
Who it’s for. Developers and researchers who need a large, uncensored language model in GGUF format. The model is suitable for local inference with llama.cpp or vLLM setups.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 11.0 GB | 12.4 GB | Too big | Get file → | |
| Q3_K_S | 13.0 GB | 14.4 GB | Too big | Get file → | |
| Q3_K_M | 14.4 GB | 15.7 GB | Too big | Get file → | |
| Q3_K_L | 15.6 GB | 16.9 GB | Too big | Get file → | |
| IQ4_XS | 16.2 GB | 17.5 GB | Too big | Get file → | |
| Q4_K_S | 17.1 GB | 18.4 GB | Too big | Get file → | |
| Q4_K_M | 18.1 GB | 19.5 GB | Too big | Get file → | |
| Q5_K_S | 20.7 GB | 22.0 GB | Too big | Get file → | |
| Q5_K_M | 21.3 GB | 22.6 GB | Too big | Get file → | |
| Q6_K | 24.6 GB | 26.0 GB | Too big | Get file → | |
| Q8_0 | 31.8 GB | 33.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (12.4 GB) or Q3_K_S (14.4 GB). With 12 GB VRAM, Q3_K_M (15.7 GB) is feasible. For 16 GB VRAM, Q4_K_S (18.4 GB) or Q4_K_M (19.5 GB) can be used. Memory estimates are approximate.
What GPU do you need for GLM 4.7 Flash Derestricted?
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 Q5_K_M (21.3 GB file, about 22.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (24.6 GB file, about 26.0 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 Derestricted quant should you choose?
Q4_K_M is the usual starting point for GLM 4.7 Flash Derestricted: 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 Q2_K at 11.0 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 GLM 4.7 Flash Derestricted
How much VRAM does GLM 4.7 Flash Derestricted 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 Derestricted on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM 4.7 Flash Derestricted GGUF?
It depends on the quant: Q2_K is 11.0 GB, Q3_K_S is 13.0 GB, Q3_K_M is 14.4 GB, Q3_K_L is 15.6 GB, IQ4_XS is 16.2 GB, Q4_K_S is 17.1 GB and 5 more.
What context length does GLM 4.7 Flash Derestricted 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 Derestricted GGUF?
The files are on Hugging Face in the mradermacher/GLM-4.7-Flash-Derestricted-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 Flash Derestricted 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.
Can I run GLM‑4.7 Flash Derestricted on 8 GB VRAM?
Yes, using the Q2_K quant which requires about 12.4 GB of VRAM at 8k context.
Does the model support image inputs?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the MIT license.