GLM 4.5 Air Derestricted needs about 75.6 GB of memory at Q4_K_M (a 73.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 26 quants, from 0.2 GB to 117.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.
GLM 4.5 Air Derestricted is a 110B-parameter GLM model in GGUF format, quantized by TMNE. Its trained context length is 128K tokens. The repository has 26 quant files, from 0.2 GB to 117.5 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 2.3 GB | Fits | Get file → | |
| IQ1_M | 37.9 GB | 39.9 GB | Too big | Get file → | |
| IQ2_XXS | 39.6 GB | 41.7 GB | Too big | Get file → | |
| IQ2_XS | 42.2 GB | 44.3 GB | Too big | Get file → | |
| IQ2_S | 42.5 GB | 44.6 GB | Too big | Get file → | |
| IQ2_M | 45.1 GB | 47.2 GB | Too big | Get file → | |
| Q2_K | 46.1 GB | 48.2 GB | Too big | Get file → | |
| Q2_K_L | 46.7 GB | 48.8 GB | Too big | Get file → | |
| IQ3_XXS | 50.3 GB (2 parts) | 52.4 GB | Too big | Get file → | |
| IQ3_XS | 50.8 GB (2 parts) | 52.9 GB | Too big | Get file → | |
| Q3_K_S | 53.4 GB (2 parts) | 55.5 GB | Too big | Get file → | |
| IQ3_M | 55.5 GB (2 parts) | 57.6 GB | Too big | Get file → | |
| Q3_K_M | 55.5 GB (2 parts) | 57.6 GB | Too big | Get file → | |
| Q3_K_L | 55.9 GB (2 parts) | 58.0 GB | Too big | Get file → | |
| Q3_K_XL | 56.5 GB (2 parts) | 58.5 GB | Too big | Get file → | |
| IQ4_XS | 60.8 GB (2 parts) | 62.9 GB | Too big | Get file → | |
| IQ4_NL | 63.1 GB (2 parts) | 65.1 GB | Too big | Get file → | |
| Q4_0 | 63.8 GB (2 parts) | 65.8 GB | Too big | Get file → | |
| Q4_K_S | 68.3 GB (2 parts) | 70.4 GB | Too big | Get file → | |
| Q4_1 | 69.5 GB (2 parts) | 71.6 GB | Too big | Get file → | |
| Q4_K_M | 73.5 GB (2 parts) | 75.6 GB | Too big | Get file → | |
| Q4_K_L | 74.0 GB (2 parts) | 76.0 GB | Too big | Get file → | |
| Q5_K_S | 78.6 GB (2 parts) | 80.6 GB | Too big | Get file → | |
| Q5_K_M | 83.7 GB (3 parts) | 85.8 GB | Too big | Get file → | |
| Q6_K | 99.2 GB (3 parts) | 101.3 GB | Too big | Get file → | |
| Q8_0 | 117.5 GB (3 parts) | 119.5 GB | Too big | Get file → |
What GPU do you need for GLM 4.5 Air 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: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (45.1 GB file, about 47.2 GB in use).
Which GLM 4.5 Air Derestricted quant should you choose?
Q4_K_M is the usual starting point for GLM 4.5 Air Derestricted: it balances file size and quality well. Here it is a 73.5 GB file.
The Q8_0 file is 117.5 GB, about 1.6 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 the first one in the table at 0.2 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 4.5 Air Derestricted
How much VRAM does GLM 4.5 Air Derestricted need?
About 75.6 GB at Q4_K_M with an 8K context window. That is the 73.5 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 4.5 Air Derestricted on an 8 GB GPU?
Yes, with the smaller files: the 0.2 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GLM 4.5 Air Derestricted GGUF?
It depends on the quant: file is 0.2 GB, IQ1_M is 37.9 GB, IQ2_XXS is 39.6 GB, IQ2_XS is 42.2 GB, IQ2_S is 42.5 GB, IQ2_M is 45.1 GB and 20 more.
What context length does GLM 4.5 Air Derestricted support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.3 GB at 32K.
Where can I download GLM 4.5 Air Derestricted GGUF?
The files are on Hugging Face in the TMNE/ArliAI_GLM-4.5-Air-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 4.5 Air 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.