---

base_model: xtools-at/Qwen3.5-2B-Qwensploit-CyberSecurity

base_model_relation: quantized

tags:

• cybersecurity
• red-team
• security-research
• penetration-testing
• vulnerability-research
• ctf
• question-answering
• text-generation
• transformers
• peft
• lora
• qwen3_5
• reasoning
• code
• uncensored
• heretic
• gguf

license: apache-2.0

language:

• en

datasets:

• saidutta69/CyberSec-Reasoning-Premium
• saidutta69/RedTeam-Premium
• saidutta69/claude-mythos-distilled-25k-clean
• saidutta69/qwen3.8-max-distillation-50k-clean

pipeline_tag: image-text-to-text

---

Qwensploit 3.5 2B: Cybersecurity and Red Team : GGUF

Static quants in GGUF format of xtools-at/Qwen3.5-2B-Qwensploit-CyberSecurity

Available model files

| Quantization | File Size |

|---|---|

| Q2_K_L | 1.1 GB |

| Q4_K_M | 1.3 GB |

| Q6_K | 1.6 GB |

| Q8_0 | 2.0 GB |

---

Qwensploit 3.5 2B: Cybersecurity and Red Team

Qwensploit is a cybersecurity-focused fine-tune of a Qwen3.5-2B model merge, designed for security reasoning, vulnerability analysis, secure coding, red-team knowledge, and technical question answering.

The model was fine-tuned using LoRA on 7,000 training examples drawn from four datasets, with an additional 350 evaluation examples.

• Base model: xtools-at/Qwen3.5-2B-MultiDistill-Megamix-6xMerge-UNCENSORED-heretic
• Method: Supervised fine-tuning (LoRA)
• License metadata: Apache-2.0, subject to upstream license compatibility review
• All Qwensploit models:

- Qwensploit 2B

- Qwensploit 4B

- Qwensploit 9B

Intended use

Designed to assist with:

• Cybersecurity research and technical question answering.
• Vulnerability analysis and secure code review.
• Defensive security, threat modeling, and incident analysis.
• Authorized penetration testing and red-team exercises.
• CTF challenges, security education, and programming assistance.

Outputs may be incorrect or unsafe. Validate generated code and recommendations, and use offensive-security capabilities only in authorized environments.

Training datasets

The training mixture was randomly selected and shuffled, with a maximum entry length of 8,000.

| Dataset | Entries | Share |

|---|---:|---:|

| CyberSec-Reasoning-Premium | 2,305 | 33% |

| RedTeam-Premium | 2,385 | 34% |

| Claude Mythos Distilled 25K — Clean | 1,385 | 20% |

| Qwen3.8-Max Distillation 50K — Clean | 925 | 13% |

| Total | 7,000 | 100% |

The mixture combines cybersecurity and red-team examples with synthetic reasoning, coding, and general instruction-following data.

Upstream dataset sources

The datasets are primarily built from the following second-level sources:

• CyberSec-Reasoning-Premium: Cybersecurity Reasoning Dataset, among other sources.
• RedTeam-Premium: Ultimate Offensive Red Team.
• Claude Mythos Distilled: WithinUsAI/claude_mythos_distilled_25k.
• Qwen distillation: r0b0tlab/qwen3.8-max-distillation-50k.

Consult all linked cards for full source provenance, dataset construction details, and licensing terms.

Base model lineage

The direct base model is xtools-at/Qwen3.5-2B-MultiDistill-Megamix-6xMerge-UNCENSORED-heretic.

The related Megamix 6xMerge model is a merge combining reasoning distillation, coding, and multi-step reasoning fine-tunes distilled from Claude Mythos,Fable and Opus. The underlying model family is Qwen3.5-2B.

Training configuration

| Parameter | Value |

|---|---|

| Epochs | 1 |

| Training entries | 7,000 |

| Evaluation entries | 350 |

| Context length | 8,192 |

| Learning rate | 2e-4 |

| Batch size | 4x8 |

| LoRA rank (r) | 16 |

| LoRA alpha | 32 |

| LoRA dropout | 0.02 |

| LoRA traget modules | all |

| Optimizer | AdamW 8-bit |

| LR scheduler | Linear |

| Weight decay | 0.002 |

| GPU | NVIDIA L4 24 GB |

Training results

Reported final metrics:

| Metric | Value |

|---|---:|

| Training loss | 0.710 |

| Evaluation loss | 0.696 |

Loss tracking by training step

| Metric \ Step | Step 66 | Step 110 | Step 154 | Step 219 |

|---|---:|---:|---:|---:|

| Training loss | 0.983 | 0.782 | 0.744 | 0.710 |

| Evaluation loss | 0.828 | 0.753 | 0.715 | 0.696 |

Loss is a training diagnostic, not a direct measure of cybersecurity accuracy or safety. Independent benchmarks are needed to assess performance.

Limitations and safety

• May generate inaccurate explanations, insecure code, or outdated security advice.
• Synthetic distillation data may contain teacher-model errors.
• Performance on real-world security tasks has not been independently established.
• Use only on systems for which testing is explicitly authorized.
• Review generated commands, code, and recommendations before use.

Licensing

Although this model's is licensed under Apache-2.0, upstream licensing must be reviewed before redistribution or commercial use. In particular, the Qwen distillation dataset documents inherited restrictions that may affect downstream use.

Review the base-model and dataset cards and for license information if necessary.

References

Base model

• xtools-at/Qwen3.5-2B-MultiDistill-Megamix-6xMerge-UNCENSORED-heretic
• Qwen/Qwen3.5-2B
• DavidAU Claude 4.6 OS variant
• Jackrong Opus reasoning distillation
• Empero Qwen3.8-2B distillation
• DavidAU Polaris HighIQ Thinking Compact
• Jackrong Qwopus3.5-2B-v3
• ertghiu256 Kimi and Opus distillation
• Qwen/Qwen3.5-2B

Training datasets

• saidutta69/CyberSec-Reasoning-Premium
• saidutta69/RedTeam-Premium
• saidutta69/claude-mythos-distilled-25k-clean
• saidutta69/qwen3.8-max-distillation-50k-clean

Second-level dataset sources

• dpevzner/Cybersecurity_Reasoning_Dataset
• WNT3D/Ultimate-Offensive-Red-Team
• WithinUsAI/claude_mythos_distilled_25k
• r0b0tlab/qwen3.8-max-distillation-50k