This card describes what is present in the repository. The public files do not document the fine-tuning dataset or provide evaluation results, so the Cyber label should be read as the repository variant name—not as a verified capability claim.

Repository contents

Variant	Approximate size	Practical use
`BF16`	1.52 GB	Highest-fidelity reference build
`Q8_0`	812 MB	High-quality local inference
`Q6_K`	630 MB	Smaller high-quality option
`Q4_K_M`	529 MB	Recommended size/quality starting point
`Q2_K_L`	484 MB	Minimum footprint; expect greater quality loss
`BF16-mmproj`	207 MB	Multimodal projector artifact; see caveat below

Run locally

With a recent llama.cpp build:

bash

llama-cli \
  -hf reaperdoesntknow/Qwen3.5-0.8-Cyber-GGUF:Q4_K_M \
  --jinja

With Ollama:

ollama run hf.co/reaperdoesntknow/Qwen3.5-0.8-Cyber-GGUF:Q4_K_M

Multimodal note

The repository includes a BF16 mmproj file and its configuration includes vision components. That establishes that a projector artifact is present; it does not establish that the end-to-end multimodal path was validated for this release. Verify image input locally before depending on it.

Intended use

Local experimentation with a small Qwen3.5 model.
CPU- and memory-constrained prototyping.
Reproducible comparison of quantization levels.

Do not treat the model as an authoritative source for security, legal, medical, or operational decisions.

Evaluation status and limitations

No benchmark results or comparison baselines are published in this repository.
The fine-tuning dataset and training recipe are not documented in the public files reviewed for this card.
Quantization reduces memory use and can change output quality.
Model outputs may be incorrect, incomplete, biased, or unsafe.
The multimodal path requires independent verification.

Lineage and license

Base model: Qwen/Qwen3.5-0.8B
Format: GGUF
Conversion tooling recorded by the repository: Unsloth / llama.cpp
License: Apache-2.0

Part of the CIx cybersecurity model collection.