New Cyber-OSINT model released
Summary
A new Cyber-OSINT AI model is released, featuring a MoE architecture trained on OSINT instructions for local execution and cyber threat intelligence tasks like attribution and geolocation.
View Cached Full Text
Cached at: 09/29/26, 10:53 AM
The Cyber-OSINT model that You can run locally.
- MoE (26B total, 4B active, 262K ctx) trained on 6,500 OSINT/CTI instructions.
- SFT for cyber threat intel and investigative work.
- Threat-actor attribution.
- IoC pivoting. Geolocation.
- Admiralty source grading.
- 262K https://t.co/XaGUauAPfk
Md Ismail Šojal 🕷️ (@0x0SojalSec): a 7B cyber model that fits on locally 8GB GPU.
- finetuned cyber/DevOps post-training datasets for offensive and defensive work.
- 32K native.
- 131K with YaRN.
Most security model are a system prompt. This one is an actual finetune.
Similar Articles
@0x0SojalSec: fully uncensored Cybersecurity-specialized model tuned on exploits, pentesting and Run locally on MacBook, delivers exp…
A fully uncensored cybersecurity-specialized AI model fine-tuned on exploits and pentesting data, designed to run locally on consumer hardware with multiple quantization options, offering expert offensive and defensive insights.
OpenAI gives cyber defenders a less-restricted new model
OpenAI has released a new, less-restricted AI model aimed at helping cyber defenders, likely enhancing security operations with fewer limitations.
Cybersecurity is local AI model's killer use case
This article analyzes the performance of local and cloud AI models in cybersecurity, showing that open source models like GLM 5.1 and deepseek-v4-flash outperform proprietary models in finding security vulnerabilities in public GitHub codebases.
More open source model from US
A new open source AI model has been released from the US.
@0x0SojalSec: Fully Uncensored Cyber-Ornith-1.5-9B-OBLITERATED You can run in your laptops. - A 9B cyber agent that actually talks to…
This post introduces Cyber-Ornith-1.5-9B-OBLITERATED, a 9-billion parameter AI model for cybersecurity that runs locally on laptops, trained on cybersecurity trajectories with zero refusal and strong performance in triage and tool-calling.