Red-team & offensive LLMs
Uncensored & pentest-oriented LLMs for CTF, red-teaming and defensive security research — public, curated.
-
Text Generation • 754B • Updated • 2.27k • 362 -
orcarouter/GLM-5.3-Flash-Uncensored-FP8
Text Generation • 321B • Updated • 12.1k • 330 -
igorls/gemma-4-12B-it-heretic-GGUF
Text Generation • 12B • Updated • 23.8k • 78 -
bartowski/WhiteRabbitNeo_WhiteRabbitNeo-V3-7B-GGUF
Text Generation • 8B • Updated • 17.2k • 37
RavichandranJ/Dolphin3-Cyber-8B-GGUF
Text Generation • 8B • Updated • 72.5k • 316Note Cyber fine-tune of Dolphin3 (pentesting/CTF/red+blue team) — installed on the 3090
AlicanKiraz0/Cybersecurity-BaronLLM_Offensive_Security_LLM_Q6_K_GGUF
Text Generation • 8B • Updated • 3.1k • 392Note BaronLLM — offensive security assistant (Llama-3.1-8B lineage)
-
DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED
Text Generation • 9B • Updated • 1.12k • 25
Blackfrost-AI/CYBER-FROST-3.8-BF16
Text Generation • 180B • Updated • 1.12k • 80Note Cyber fine-tune of Qwen3.8-Flash-Next (qwen4_exp, 180B MoE) shipped with its own red/blue/purple harness. The only cyber angle on Flash-Next. Research use.
philbert440/Qwen3.8-27B-Uncensored-Cyber-GGUF
Image-Text-to-Text • 27B • Updated • 550k • 80Note Gen 3.8 avec angle cyber-specific (tag `cyber`) — usage CTF / red-team / recherche.
-
orcarouter/Qwen3.8-27B-Uncensored-FP8
Image-Text-to-Text • 28B • Updated • 56k • 1.9k
audnai/penclaw-Kimi-K3.0-abliterated-GGUF
2.8T • Updated • 157 • 249Note Kimi K3.0 abliterated — famille absente des collections, gen frontier. Usage CTF / red-team / recherche.
xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
Text Generation • 9B • Updated • 32.4k • 9.44kNote Heretic-ablated Qwen3.5-9B distilled from DeepSeek-V4-Pro reasoning traces. 4.8k likes, 21k downloads. The distillation angle is what the other Qwen3.5-9B ablations here lack.
huihui-ai/Huihui-Xing4.0-29B-A4B-abliterated
Text Generation • 31B • Updated • 360 • 27Note Xing4.0 29B-A4B (China Telecom, ex-TeleChat) abliterated: a family absent from the other collections. CTF / research use.
-
Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated
Text Generation • 35B • Updated • 188 • 19 -
Abiray/Huihui-Qwen3.6-27B-abliterated-Q4_K_M-GGUF
Text Generation • 27B • Updated • 1.18k • 7
HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Image-Text-to-Text • 35B • Updated • 1.41M • 4.19kNote Uncensored take on the Qwen3.6-35B-A3B daily driver (CTF/research use)
dealignai/Gemma-4-31B-JANG_4M-CRACK
Image-Text-to-Text • 20B • Updated • 12.3k • 1.79kNote Abliterated Gemma 4 31B — largest dense abliterated in the lineup (research use)
-
DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED
Image-Text-to-Text • 9B • Updated • 872 • 247 -
huihui-ai/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated
Image-Text-to-Text • 28B • Updated • 203 • 131 -
huihui-ai/Huihui-Qwen3.5-9B-abliterated
Image-Text-to-Text • 10B • Updated • 7.76k • 182 -
WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B
Text Generation • 8B • Updated • 2.29k • 90 -
drowzeys/DeepSeek-V4.1-Flash-Abliterated-Cybersecurity-Unleashed
Image-Text-to-Text • Updated • 272 -
cyjin-yl/Qwen3.8-27B-Uncensored-Cyber-agentic-imatrix-GGUF
Image-Text-to-Text • 3.39M • Updated • 334k • 265 -
BugTraceAI/BugTraceAI-Apex-G4-26B-Master-f16
25B • Updated • 1.74k • 18 -
freakyskittle/CYBER-FROST-3.8-GGUF
Image-Text-to-Text • 177B • Updated • 15.6k • 26 -
mradermacher/Cyber-Ornith-1.5-9B-OBLITERATED-i1-GGUF
9B • Updated • 845k • 72 -
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF
Image-Text-to-Text • 27B • Updated • 4.29M • 2.27k -
OBLITERATUS
💥630One-click model liberation + chat playground
-
HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP
Image-Text-to-Text • 25B • Updated • 505k • 375 -
huihui-ai/Huihui-Qwen3.8-Flash-Next-abliterated-v2-GGUF
Image-Text-to-Text • 3B • Updated • 943k • 265