Curated List of Uncensored Open-Weight Models for Offensive Security Surfaces on GitHub
cyb3rops · x · 2026-09-29
A GitHub repo curates open-weight uncensored LLMs fine-tuned for authorized red team operations, penetration testing, and security research, sourced from HuggingFace model cards. Highlights include DeepHat V2 (WhiteRabbitNeo, based on Qwen2.5-Coder 7B/32B, SFT on 1.7M offensive/defensive samples, 6GB VRAM at Q4, Apache 2.0) and BugTraceAI-CORE-Apex (26B MoE trained on HackerOne Hacktivity reports and WAF evasion data, 16GB VRAM), among other security-specific fine-tunes.
More from Models
- 'My own personal move 37': users report Claude and Fable 5.1 proposing genuinely good ideas they missed — zetalyrae · 2026-09-29
- ElevenLabs v4 Voice Model Now Available on Runway Platform — runwayml · 2026-09-29
- Anthropic ships Sonnet 5.5 at half the price, nearly matching Opus 5.5; Haiku 5.5 on the way — oran_ge · 2026-09-29
- Latent Space: TypeSafe CEO on why he rejects public benchmarks for Jev — Latent Space · 2026-09-29
- Xiaomi MiMo-V2.6-Distill-Qwen-9B GGUF quantization trends on Hugging Face — bartowski · 2026-09-29
- Grok 4.7 hits Amazon Bedrock: 500K context, 2x output tokens for the gains — AWS ML Blog · 2026-09-29