GLM 4.5 Air needs about 74.9 GB of memory at Q4_K_M (a 72.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 45.0 GB (Q2_K) 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 is a 110B-parameter GLM model in GGUF format, quantized by John1604. Its trained context length is 128K tokens. The repository has 8 quant files, from 45.0 GB (Q2_K) to 117.5 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 45.0 GB | 47.0 GB | Too big | Get file → | |
| Q3_K_S | 52.4 GB | 54.4 GB | Too big | Get file → | |
| Q3_K_M | 57.0 GB | 59.1 GB | Too big | Get file → | |
| IQ4_NL | 63.0 GB | 65.1 GB | Too big | Get file → | |
| Q4_K_M | 72.9 GB | 74.9 GB | Too big | Get file → | |
| Q5_K | 83.4 GB | 85.5 GB | Too big | Get file → | |
| Q6_K | 99.0 GB | 101.1 GB | Too big | Get file → | |
| Q8_0 | 117.5 GB | 119.5 GB | Too big | Get file → |
What GPU do you need for GLM 4.5 Air?
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: the best quant that fits is Q2_K (45.0 GB file, about 47.0 GB in use).
Which GLM 4.5 Air quant should you choose?
Q4_K_M is the usual starting point for GLM 4.5 Air: it balances file size and quality well. Here it is a 72.9 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 Q2_K at 45.0 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 4.5 Air
How much VRAM does GLM 4.5 Air need?
About 74.9 GB at Q4_K_M with an 8K context window. That is the 72.9 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 47.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM 4.5 Air GGUF?
It depends on the quant: Q2_K is 45.0 GB, Q3_K_S is 52.4 GB, Q3_K_M is 57.0 GB, IQ4_NL is 63.0 GB, Q4_K_M is 72.9 GB, Q5_K is 83.4 GB and 2 more.
What context length does GLM 4.5 Air 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 GGUF?
The files are on Hugging Face in the John1604/GLM-4.5-Air-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 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.