AdversariaLLM

Security research models, measured.

Curated detection-engineering, malware-analysis and threat-intel models.

All models
Capability
2 of 25
Threat detection & defense2

Llama-Primus-Merged

Security assistant

CTI · CISSP · CVE mapping · Q4_K_M

Trend Micro's Primus continued-pretrain merged into Llama-3.1-8B-Instruct — domain gains with general capability retained.

8K ctx
$0.15 in · $0.60 out
per Mtok · Available
not scored yet
model page, scores and worked example →

ZySec-7B

Security helper

CTI · security Q&A · cloud security · Q4_K_M

A Mistral-7B security assistant tuned for defensive cyber threat intelligence, security Q&A, and cloud security.

32K ctx ?
not yet priced
Coming soon
not scored yet
model page, scores and worked example →
Model catalog — measured, not marketed · AdversariaLLM