CybersecurityText

Foundation-Sec

Cisco models for information security based on Llama 3.1 8B: analysis of vulnerabilities, threats and incidents. Can be deployed inside your own perimeter.

Developer
Cisco (Foundation AI), USA
First release
Apr 2025
Latest release
Jan 2026
Sizes
8B
License
Commercial use with conditionsBase model is Apache 2.0; Instruct and Reasoning — Cisco's changes under Apache 2.0 plus the Llama 3.1 Community License
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Security, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Analyzing vulnerability and threat reports
  • Helping SOC analysts during incidents
  • Mapping threats to MITRE ATT&CK

Where it is used

Security teams and SOCsIntegrators and MSSPsSecurity product development

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Foundation-Sec-8B-Reasoning
  2. Foundation-Sec-1.1-8B-Instruct (контекст 64k)
  3. Foundation-Sec-8B-Instruct
  4. Foundation-Sec-8B (базовая)

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Foundation-Sec be used in a commercial project?

With conditions. License: Base model is Apache 2.0; Instruct and Reasoning — Cisco's changes under Apache 2.0 plus the Llama 3.1 Community License. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Foundation-Sec need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Foundation-Sec support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Foundation-Sec and what does it cost?

The Foundation-Sec weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

CybersecurityLlama-PrimusTrend Micro · JapanCommercial use with conditions

Trend Micro cybersecurity models based on Llama 3.1 8B, fine-tuned on a corpus of security texts. A reasoning version is available.

DetailsTextLlamaMeta · USACommercial use with conditions

The models that started mass open source in AI. A huge ecosystem of fine-tuned versions and tools.

Details

Source: huggingface.co/fdtn-ai/Foundation-Sec-8B-Reasoning. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.