Foundation Sec 8B Reasoning needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
8‑Billion parameter LLaMA‑3.1 model specialized for cybersecurity reasoning
Foundation‑Sec‑8B‑Reasoning is an 8‑B parameter instruction‑tuned LLaMA‑3.1 model focused on security tasks. It extends the base Foundation‑Sec‑8B with reasoning capabilities and is optimized for SOC acceleration, threat defense, and engineering enablement. The model is designed for local deployment in secure environments.
Good at
- Reasoning about security scenarios
- Instruction following for security workflows
- Summarizing threat intelligence
Limits
- No vision support
- Requires ~6.5 GB RAM at 8 k context
- License is other – see NOTICE.md
Best for
- SOC triage automation
- Vulnerability prioritization
- Security configuration validation
Who it’s for. Security practitioners, researchers, and developers building AI‑powered security tools. The model is intended for local deployment where data security and regulatory compliance are priorities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 4.9 GB | 6.5 GB | Fits | Get file → |
The Q4_K_M quantized checkpoint is 4.92 GB on disk and requires about 6.5 GB of RAM at 8 k context. For systems with 8 GB VRAM, this quant is suitable. If memory is limited, consider a higher‑bit quant if available, but only Q4_K_M is listed.
What GPU do you need for Foundation Sec 8B Reasoning?
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: the best quant that fits is Q4_K_M (4.9 GB file, about 6.5 GB in use).
Which Foundation Sec 8B Reasoning quant should you choose?
Q4_K_M is the usual starting point for Foundation Sec 8B Reasoning: it balances file size and quality well. Here it is a 4.9 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Foundation Sec 8B Reasoning
How much VRAM does Foundation Sec 8B Reasoning need?
About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Foundation Sec 8B Reasoning on an 8 GB GPU?
Yes, with Q4_K_M: the 4.9 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Foundation Sec 8B Reasoning GGUF?
It depends on the quant: Q4_K_M is 4.9 GB.
What context length does Foundation Sec 8B Reasoning support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Foundation Sec 8B Reasoning GGUF?
The files are on Hugging Face in the fdtn-ai/Foundation-Sec-8B-Reasoning-Q4_K_M-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 Foundation Sec 8B Reasoning use?
Hugging Face lists the license as other. 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 Foundation‑Sec‑8B‑Reasoning on 8 GB VRAM?
Yes, the Q4_K_M quantized model requires about 6.5 GB of RAM, which fits within 8 GB VRAM when loaded with llama.cpp.
Does the model support multiple languages?
No, the model is trained only for English.
Is the model open‑source?
The model is open‑weight but licensed under an other license; see NOTICE.md for details.