cerebras/GLM-4.5-Air-REAP-82B-A12B needs about 58.0 GB of memory at Q4_K_M (a 55.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 34.6 GB (Q2_K) to 170.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.
cerebras/GLM-4.5-Air-REAP-82B-A12B is a 85B-parameter GLM model in GGUF format, quantized by DevQuasar. Its trained context length is 128K tokens. The repository has 5 quant files, from 34.6 GB (Q2_K) to 170.0 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 34.6 GB | 36.7 GB | Too big | Get file → | |
| Q3_K_M | 43.9 GB (4 parts) | 45.9 GB | Too big | Get file → | |
| Q4_K_M | 55.9 GB (5 parts) | 58.0 GB | Too big | Get file → | |
| Q5_K_M | 64.1 GB (5 parts) | 66.2 GB | Too big | Get file → | |
| F16 | 170.0 GB (5 parts) | 172.1 GB | Too big | Get file → |
What GPU do you need for cerebras/GLM-4.5-Air-REAP-82B-A12B?
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 Q3_K_M (43.9 GB file, about 45.9 GB in use).
Which cerebras/GLM-4.5-Air-REAP-82B-A12B quant should you choose?
Q4_K_M is the usual starting point for cerebras/GLM-4.5-Air-REAP-82B-A12B: it balances file size and quality well. Here it is a 55.9 GB file.
If memory is tight, the smallest file is Q2_K at 34.6 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 cerebras/GLM-4.5-Air-REAP-82B-A12B
How much VRAM does cerebras/GLM-4.5-Air-REAP-82B-A12B need?
About 58.0 GB at Q4_K_M with an 8K context window. That is the 55.9 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 cerebras/GLM-4.5-Air-REAP-82B-A12B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 36.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of cerebras/GLM-4.5-Air-REAP-82B-A12B GGUF?
It depends on the quant: Q2_K is 34.6 GB, Q3_K_M is 43.9 GB, Q4_K_M is 55.9 GB, Q5_K_M is 64.1 GB, F16 is 170.0 GB.
What context length does cerebras/GLM-4.5-Air-REAP-82B-A12B 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 cerebras/GLM-4.5-Air-REAP-82B-A12B GGUF?
The files are on Hugging Face in the DevQuasar/cerebras.GLM-4.5-Air-REAP-82B-A12B-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 cerebras/GLM-4.5-Air-REAP-82B-A12B 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.