GLM-4.5-Air-Derestricted needs about 103.1 GB of memory at Q8_0 (a 101.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 68.6 GB (Q8_0) to 220.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.
GLM‑4.5‑Air‑Derestricted – a 110B parameter reasoning model
GLM‑4.5‑Air‑Derestricted is a 110B parameter model from the GLM family. It is a derestricted version of GLM‑4.5‑Air, produced by Arli AI. The model is trained on 131072 context tokens and is licensed under MIT.
Good at
- Reasoning
- Tool use
- Large context handling
Limits
- No vision support
- Requires high VRAM for full precision
- Mixture of experts may increase memory
Best for
- Complex reasoning tasks
- Tool‑integrated workflows
- Long‑form content generation
Who it’s for. Developers and researchers who need a large‑parameter model with strong reasoning and tool‑use capabilities. The model is suitable for applications that can accommodate its memory requirements and do not require vision or multimodal inputs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 68.6 GB | 70.7 GB | Too big | Get file → | |
| Q8_0 | 92.0 GB | 94.1 GB | Too big | Get file → | |
| Q8_0 | 101.0 GB | 103.1 GB | Too big | Get file → | |
| Q8_0 | 117.5 GB | 119.5 GB | Too big | Get file → | |
| BF16 | 220.1 GB (2 parts) | 222.2 GB | Too big | Get file → |
For 8 GB VRAM use Q8_0 with a file size of 68.64 GB; estimated memory at 8 k context is 70.7 GB. For 16 GB VRAM use the Q8_0 file of 91.99 GB; estimated memory is 94.1 GB. If more VRAM is available, the 101.01 GB Q8_0 file uses 103.1 GB memory. The BF16 split into shards requires 220.11 GB and 222.2 GB memory.
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: 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-4.5-Air-Derestricted quant should you choose?
Q8_0 (101.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is Q8_0 at 68.6 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
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 103.1 GB at Q8_0 with an 8K context window. That is the 101.0 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?
Not at an 8K context. The smallest file needs about 70.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM-4.5-Air-Derestricted GGUF?
It depends on the quant: Q8_0 is 68.6 GB, Q8_0 is 92.0 GB, Q8_0 is 101.0 GB, Q8_0 is 117.5 GB, BF16 is 220.1 GB.
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 ddh0/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.
Can I run GLM‑4.5‑Air‑Derestricted on 8 GB VRAM?
No. The smallest Q8_0 quant requires 70.7 GB memory at 8 k context, which exceeds 8 GB VRAM.
Does this model support vision or multimodal input?
No. The model only handles text and does not include vision capabilities.
What license applies to this model?
The model is released under the MIT license.