---
format: "aidr-story-markdown/v1"
id: "bfd5fc99daf50570b5de6d9cb23adf2cd36e30b3523b0d0a0e8d8e647f4f3b12"
canonical_url: "https://aidr.today/bfd5fc99?lang=en"
title: "New Cyber-OSINT model released"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-29T10:23:33.000Z"
category: "Models"
topics: ["llm"]
source_urls: ["https://twitter.com/0x0SojalSec/status/2104736980768866439","https://news.ycombinator.com/item?id=49890829"]
summary: "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 context."
---

# New Cyber\-OSINT model released

> [Open the canonical story](<https://aidr.today/bfd5fc99?lang=en>)

**Published:** 2026-09-29T10:23:33.000Z
**Category:** Models
**Topics:** llm

## Summary

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 context\.

## Sources

- [Story source](<https://twitter.com/0x0SojalSec/status/2104736980768866439>)
- [Discussion](<https://news.ycombinator.com/item?id=49890829>)