Skip to content
Computer vision

Qwensploit V2 9B - Cybersecurity & Red Team

a specialized language model for information security

2 min readupdated

This 9.4B-parameter model is an optimized fine-tune of xtools-at/Qwen3.5-9B-Claude-3xMerge-UNCENSORED-heretic, built to assist cybersecurity specialists, pentesters, and vulnerability researchers. Unlike the first version, the developers manually cleaned and filtered the datasets, dropping raw CVE (Common Vulnerabilities and Exposures — the public catalog of security flaws) dumps in favor of high-quality instructions and logical reasoning. The result is a reliable technical assistant for code analysis, CTF challenges, and security audits.

Key features

  • Infosec focus: Trained on 14.4k carefully curated examples, including web security and incident data.
  • Improved soft reasoning: Incorporates distillation datasets for deep logical analysis of complex technical problems.
  • Clean data: All datasets were manually inspected and filtered to eliminate contradictory responses.
  • Capable base: Built on a strong, unrestricted foundation supporting a context length of up to 8192 tokens.

What you can do

  • Code auditing: Run security reviews on source code, hunt for vulnerabilities, and refine patches.
  • Threat research: Break down attack vectors and draft security incident reports.
  • Solving CTF challenges: Use the model as a sparring partner for competitive infosec tasks.
  • Infosec learning: Study penetration testing and network security fundamentals through structured technical explanations.

Example

Sample prompt for analyzing web application security: "Analyze this PHP code snippet for SQL injection vulnerabilities and suggest a secure version using prepared statements."

Read moreDetails
Training method: 16bit LoRA SFT (low-rank adaptation for efficient fine-tuning)
Dataset size: 14,400+ training samples, epochs: 1
Hyperparameters: LR 2e-4, LoRA rank 16, LoRA alpha 32
Limitations: Generated commands and code must be verified in an isolated environment
Discuss Telegram 0 1

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 18 GB · ready files20 GB
  • FP8 / INT8recommendedweights 8.8 GB10 GB
  • 4-bitweights 4.9 GB5.9 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2080 Ti · BF16 — from RTX 4090

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # fantasyx07/Qwensploit-V2-9B-CyberSecurity-Qwen3.5
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download fantasyx07/Qwensploit-V2-9B-CyberSecurity-Qwen3.5 --local-dir ~/models/Qwensploit-V2-9B-CyberSecurity-Qwen3.5
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

  1. Qwen3.5-9B-Basefamily root
  2. Qwen3.5-9B
  3. Qwen3.5-9B-Claude-3xMerge
  4. Qwen3.5-9B-Claude-3xMerge-UNCENSORED-heretic
  5. Qwensploit-V2-9B-CyberSecurity-Qwen3.5

New posts about versions of Qwen3.5-9B-Base (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 6All on Hugging Face
Merges 1All on Hugging Face

About the model

fantasyx07/Qwensploit-V2-9B-CyberSecurity-Qwen3.5
Author
fantasyx07
Category
Computer vision
Released
Posted

On NeyroLearn

Hugging Face

10

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments