GPT OSS Cybersecurity Merged 20B Heretic Ara needs about 16.7 GB of memory at Q4_K_M (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 12.1 GB (Q3_K_S) to 41.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
GPT OSS Cybersecurity Merged 20B Heretic Ara – 20.9B parameter MoE model for cybersecurity tasks
GPT OSS Cybersecurity Merged 20B Heretic Ara is a 20.9B parameter Mixture of Experts model fine‑tuned on cybersecurity instruction‑response data. It supports tools and offers specialized capabilities such as threat analysis, incident response guidance, and vulnerability assessment.
Good at
- Cybersecurity threat analysis
- Incident response guidance
- Vulnerability assessment
Limits
- Requires 40GB+ VRAM for BF16 inference
- No vision support
- License is apache-2.0
Best for
- Security analysts evaluating threat data
- Incident response teams drafting mitigation plans
- Vulnerability researchers testing detection methods
Who it’s for. This model is intended for security professionals and researchers who need a specialized LLM for cybersecurity workflows. It is suitable for teams with access to high‑memory GPUs and who require tool integration.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 12.1 GB | 13.0 GB | Too big | Get file → | |
| Q2_K | 12.1 GB | 13.0 GB | Too big | Get file → | |
| TQ1_0 | 12.1 GB | 13.0 GB | Too big | Get file → | |
| TQ2_0 | 12.1 GB | 13.0 GB | Too big | Get file → | |
| Q4_0 | 12.1 GB | 13.0 GB | Too big | Get file → | |
| MXFP4_MOE | 12.1 GB | 13.0 GB | Too big | Get file → | |
| Q3_K | 12.9 GB | 13.8 GB | Too big | Get file → | |
| Q3_K_M | 12.9 GB | 13.8 GB | Too big | Get file → | |
| Q3_K_L | 13.3 GB | 14.2 GB | Too big | Get file → | |
| Q4_1 | 13.4 GB | 14.3 GB | Too big | Get file → | |
| Q5_0 | 14.6 GB | 15.5 GB | Too big | Get file → | |
| Q4_K_S | 14.7 GB | 15.6 GB | Too big | Get file → | |
| Q4_K | 15.8 GB | 16.7 GB | Too big | Get file → | |
| Q4_K_M | 15.8 GB | 16.7 GB | Too big | Get file → | |
| Q5_K_S | 15.9 GB | 16.8 GB | Too big | Get file → | |
| Q5_1 | 15.9 GB | 16.8 GB | Too big | Get file → | |
| Q5_K | 16.9 GB | 17.8 GB | Too big | Get file → | |
| Q5_K_M | 16.9 GB | 17.8 GB | Too big | Get file → | |
| Q6_K | 22.2 GB | 23.1 GB | Too big | Get file → | |
| Q8_0 | 22.3 GB | 23.2 GB | Too big | Get file → | |
| BF16 | 41.9 GB | 42.8 GB | Too big | Get file → | |
| F16 | 41.9 GB | 42.8 GB | Too big | Get file → |
For 8‑GB VRAM, use Q3_K_S (12.06 GB file, 13 GB memory at 8k context). For 16‑GB VRAM, Q4_K (15.81 GB file, 16.7 GB memory). For 24‑GB VRAM, Q5_K (16.89 GB file, 17.8 GB memory). Memory estimates are approximate.
What GPU do you need for GPT OSS Cybersecurity Merged 20B Heretic Ara?
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: the best quant that fits is Q4_K_S (14.7 GB file, about 15.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (22.3 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (22.3 GB file, about 23.2 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (41.9 GB file, about 42.8 GB in use).
Which GPT OSS Cybersecurity Merged 20B Heretic Ara quant should you choose?
Q4_K_M is the usual starting point for GPT OSS Cybersecurity Merged 20B Heretic Ara: it balances file size and quality well. Here it is a 15.8 GB file.
The Q8_0 file is 22.3 GB, about 1.4 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 Q3_K_S at 12.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about GPT OSS Cybersecurity Merged 20B Heretic Ara
How much VRAM does GPT OSS Cybersecurity Merged 20B Heretic Ara need?
About 16.7 GB at Q4_K_M with an 8K context window. That is the 15.8 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 GPT OSS Cybersecurity Merged 20B Heretic Ara on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GPT OSS Cybersecurity Merged 20B Heretic Ara GGUF?
It depends on the quant: Q3_K_S is 12.1 GB, Q2_K is 12.1 GB, TQ1_0 is 12.1 GB, TQ2_0 is 12.1 GB, Q4_0 is 12.1 GB, MXFP4_MOE is 12.1 GB and 16 more.
What context length does GPT OSS Cybersecurity Merged 20B Heretic Ara support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download GPT OSS Cybersecurity Merged 20B Heretic Ara GGUF?
The files are on Hugging Face in the piotreknow02/GPT-OSS-Cybersecurity-Merged-20B-heretic-ara-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 GPT OSS Cybersecurity Merged 20B Heretic Ara 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.
Can I run this model on 8 GB VRAM?
Yes, using Q3_K_S quantization which requires about 13 GB of VRAM at 8k context.
Does the model support image inputs?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.