GLM 4.5 Air REAP 82B A12B heretic needs about 56.0 GB of memory at Q4_K_M (a 53.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 33.0 GB (IQ2_M) to 163.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.2 GB.
GLM 4.5 Air REAP 82B A12B heretic – a large mixture‑of‑experts LLM
GLM 4.5 Air REAP 82B A12B heretic is a 82 billion‑parameter model with 12 billion active parameters. It supports a context length of 131 072 tokens and is released under the MIT license. The model is available in multiple GGUF quantizations.
Good at
- Large context handling
- Mixture‑of‑experts inference
- High token throughput
Limits
- No vision support
- Requires significant VRAM for full precision
- License is MIT – no restrictions
Best for
- Long‑form content generation
- Complex reasoning tasks
- Research prototyping
Who it’s for. Engineers and researchers needing a large‑scale language model with extensive context. The model is suitable for environments where GPU memory is ample and the MIT license is acceptable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 33.0 GB | 35.1 GB | Too big | Get file → | |
| IQ3_M | 39.5 GB | 41.5 GB | Too big | Get file → | |
| IQ4_XS | 44.6 GB | 46.6 GB | Too big | Get file → | |
| IQ4_NL | 46.3 GB | 48.4 GB | Too big | Get file → | |
| Q4_K_M | 53.9 GB | 56.0 GB | Too big | Get file → | |
| Q5_K_M | 61.8 GB | 63.8 GB | Too big | Get file → | |
| Q6_K | 73.4 GB | 75.4 GB | Too big | Get file → | |
| BF16 | 163.9 GB | 166.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_M (33.03 GB file, ~35.1 GB memory at 8 k context). For 16 GB VRAM, Q4_K_M (53.92 GB file, ~56 GB memory) is a good balance. For 32 GB VRAM, BF16 (163.91 GB file, ~166 GB memory) provides full precision.
What GPU do you need for GLM 4.5 Air REAP 82B A12B heretic?
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 IQ4_XS (44.6 GB file, about 46.6 GB in use).
Which GLM 4.5 Air REAP 82B A12B heretic quant should you choose?
Q4_K_M is the usual starting point for GLM 4.5 Air REAP 82B A12B heretic: it balances file size and quality well. Here it is a 53.9 GB file.
If memory is tight, the smallest file is IQ2_M at 33.0 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
Frequently asked questions about GLM 4.5 Air REAP 82B A12B heretic
How much VRAM does GLM 4.5 Air REAP 82B A12B heretic need?
About 56.0 GB at Q4_K_M with an 8K context window. That is the 53.9 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 REAP 82B A12B heretic on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 35.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GLM 4.5 Air REAP 82B A12B heretic GGUF?
It depends on the quant: IQ2_M is 33.0 GB, IQ3_M is 39.5 GB, IQ4_XS is 44.6 GB, IQ4_NL is 46.3 GB, Q4_K_M is 53.9 GB, Q5_K_M is 61.8 GB and 2 more.
What context length does GLM 4.5 Air REAP 82B A12B heretic support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.5 GB at 8K and 6.2 GB at 32K.
Where can I download GLM 4.5 Air REAP 82B A12B heretic GGUF?
The files are on Hugging Face in the jtl11/GLM-4.5-Air-REAP-82B-A12B-heretic-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 REAP 82B A12B heretic 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 this model on 8 GB VRAM?
Only the lowest quantization IQ2_M can fit, but it will still require ~35.1 GB memory at 8 k context, so 8 GB VRAM is insufficient.
Does the model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the MIT license.