CoolFace
Modelpublic

reaperdoesntknow/Qwen3.5-2B-CyberSec-GGUF

sourceHugging Faceapache-2.0updated 20h agoView on Hugging Face
0likes7.3kdownloads
Model Card

Qwen3.5-2B-CyberSec — GGUF

GGUF exports of reaperdoesntknow/Qwen3.5-2B-CyberSec for local inference with llama.cpp-compatible runtimes.

The source model is associated with the Trendyol Cybersecurity Instruction Tuning Dataset. No benchmark or safety-evaluation results are published with this GGUF release.

Available files

FileReported sizePractical use
Qwen3.5-2B.BF16.gguf3.90 GBHighest-fidelity GGUF build
Qwen3.5-2B.Q8_0.gguf2.08 GBHigh-quality quantized build
Qwen3.5-2B.Q4_K_M.gguf1.31 GBRecommended local starting point
Qwen3.5-2B.BF16-mmproj.ggufrepository artifactMultimodal projector; see caveat below

Run locally

bash
llama-cli \
  -hf reaperdoesntknow/Qwen3.5-2B-CyberSec-GGUF:Q4_K_M \
  --jinja

With Ollama:

bash
ollama run hf.co/reaperdoesntknow/Qwen3.5-2B-CyberSec-GGUF:Q4_K_M

Multimodal note

A BF16 projector file is present, and the source-model configuration includes vision components. This release does not include a documented multimodal smoke-test receipt. Verify the projector, prompt format, runtime version, and image path before claiming multimodal support.

Intended use

  • —Local qualitative evaluation of the source checkpoint.
  • —CPU or consumer-GPU experimentation.
  • —Comparison of BF16, Q80, and Q4K_M output quality.

Limitations and safety

  • —Quantization can change quality and behavior relative to the source checkpoint.
  • —The release has no published benchmark, regression, or safety report.
  • —Generated security instructions may be wrong, unsafe, or dual use.
  • —Do not execute generated commands without review and isolation.
  • —Do not rely on the model as an authoritative security control or decision-maker.

Lineage and license

Part of the CIx cybersecurity model collection. <!-- cix-keeper-ts:2026-09-23T13:16:42Z -->