Ferr0 PRO

Ferr0

ferr079
ferr079

AI & ML interests

Infra-minded AI builder — local LLM inference (Ollama / vLLM on a home RTX 3090), structured generation & tool-calling, offline RAG, and defensive AI security. Self-hostable, reproducible demos.

Recent Activity

liked a model about 11 hours ago

empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF

updated a collection about 24 hours ago

Red-team & offensive LLMs

liked a model about 24 hours ago

huihui-ai/Huihui-GLM-5.2-abliterated-GGUF

View all activity

Organizations

None yet

Ferr0 's collections 4

Red-team & offensive LLMs

Uncensored & pentest-oriented LLMs for CTF, red-teaming and defensive security research — public, curated.

igorls/gemma-4-12B-it-heretic-GGUF

Text Generation • 12B • Updated 26 days ago • 52.7k • 40
Abiray/Huihui-Qwen3.6-27B-abliterated-Q4_K_M-GGUF

Text Generation • 27B • Updated Apr 23 • 549 • 6
bartowski/WhiteRabbitNeo_WhiteRabbitNeo-V3-7B-GGUF

Text Generation • 8B • Updated May 22, 2025 • 2.52k • 7
huihui-ai/Huihui-GLM-5.2-abliterated-GGUF

Text Generation • 754B • Updated about 9 hours ago • 65 • 96

Structured output & tool-calling

Forcing LLMs to emit schema-valid JSON and call tools reliably — the engine room of agentic, production-grade AI.

Running on Zero

Agents

Structured Output Playground

🔒

Lock any LLM's output to a JSON schema
Qwen/Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Jan 12, 2025 • 12.7M • • 1.39k
NousResearch/Hermes-2-Pro-Llama-3-8B

Text Generation • 8B • Updated Sep 14, 2024 • 20.6k • • 453
Salesforce/xlam-function-calling-60k

Viewer • Updated Jan 24, 2025 • 60k • 22.2k • 642

Defensive AI & code security

Auditing and guarding with LLMs — adversarial code review, prompt-injection and content guardrails. Report only what you can exploit.

Running on Zero

Agents

Adversarial SAST

🛡

Adversarial SAST — false positives die on screen
Running

Agents

136

OpenMythos

🛡

136

An Open Source Cyber Security Agent
meta-llama/Llama-Guard-3-8B

Text Generation • 8B • Updated Oct 11, 2024 • 243k • • 307
Qwen/Qwen2.5-Coder-7B-Instruct

Text Generation • 8B • Updated Jan 12, 2025 • 1.94M • • 744

Local-first LLMs

Small, capable models I run locally on a single RTX 3090 (Ollama / llama.cpp / transformers) — the backbone of self-hosted, sovereign AI.

Qwen/Qwen3.6-27B

Image-Text-to-Text • 28B • Updated Apr 24 • 5.26M • • 1.85k
Qwen/Qwen3.5-4B

Image-Text-to-Text • 5B • Updated Mar 2 • 8.4M • • 703
google/gemma-4-12B-it

Any-to-Any • 12B • Updated 26 days ago • 2.62M • 1.22k
Qwen/Qwen3-Coder-30B-A3B-Instruct

Text Generation • 31B • Updated Dec 3, 2025 • 1.75M • • 1.14k

Red-team & offensive LLMs

Uncensored & pentest-oriented LLMs for CTF, red-teaming and defensive security research — public, curated.

igorls/gemma-4-12B-it-heretic-GGUF

Text Generation • 12B • Updated 26 days ago • 52.7k • 40
Abiray/Huihui-Qwen3.6-27B-abliterated-Q4_K_M-GGUF

Text Generation • 27B • Updated Apr 23 • 549 • 6
bartowski/WhiteRabbitNeo_WhiteRabbitNeo-V3-7B-GGUF

Text Generation • 8B • Updated May 22, 2025 • 2.52k • 7
huihui-ai/Huihui-GLM-5.2-abliterated-GGUF

Text Generation • 754B • Updated about 9 hours ago • 65 • 96

Defensive AI & code security

Auditing and guarding with LLMs — adversarial code review, prompt-injection and content guardrails. Report only what you can exploit.

Running on Zero

Agents

Adversarial SAST

🛡

Adversarial SAST — false positives die on screen
Running

Agents

136

OpenMythos

🛡

136

An Open Source Cyber Security Agent
meta-llama/Llama-Guard-3-8B

Text Generation • 8B • Updated Oct 11, 2024 • 243k • • 307
Qwen/Qwen2.5-Coder-7B-Instruct

Text Generation • 8B • Updated Jan 12, 2025 • 1.94M • • 744

Structured output & tool-calling

Forcing LLMs to emit schema-valid JSON and call tools reliably — the engine room of agentic, production-grade AI.

Running on Zero

Agents

Structured Output Playground

🔒

Lock any LLM's output to a JSON schema
Qwen/Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Jan 12, 2025 • 12.7M • • 1.39k
NousResearch/Hermes-2-Pro-Llama-3-8B

Text Generation • 8B • Updated Sep 14, 2024 • 20.6k • • 453
Salesforce/xlam-function-calling-60k

Viewer • Updated Jan 24, 2025 • 60k • 22.2k • 642

Local-first LLMs

Small, capable models I run locally on a single RTX 3090 (Ollama / llama.cpp / transformers) — the backbone of self-hosted, sovereign AI.

Qwen/Qwen3.6-27B

Image-Text-to-Text • 28B • Updated Apr 24 • 5.26M • • 1.85k
Qwen/Qwen3.5-4B

Image-Text-to-Text • 5B • Updated Mar 2 • 8.4M • • 703
google/gemma-4-12B-it

Any-to-Any • 12B • Updated 26 days ago • 2.62M • 1.22k
Qwen/Qwen3-Coder-30B-A3B-Instruct

Text Generation • 31B • Updated Dec 3, 2025 • 1.75M • • 1.14k

Ferr0 PRO

AI & ML interests

Recent Activity

Organizations

Ferr0 's collections 4

Structured Output Playground

Adversarial SAST

OpenMythos

Adversarial SAST

OpenMythos

Structured Output Playground