CyberStrike OffSec 35B

Q5_K · huihui-ai · Preserved candidate · quality ungraded

The selected Q5_K GGUF of huihui-ai's abliterated CyberStrike OffSec 35B release.

Benchmark results · Files · Download · Runtime · Provenance · Full collection

Join Infinity on Discord

Get model support, request models and quants, discuss benchmarks, and follow new releases and model improvements.

Join the Infinity community

All model tests, per-question scores, experiment history and scoring methods

Qwen effort study — separate full-404 cohort: medium 82.87/100 versus xhigh 84.41/100; paired difference +1.54 points (95% interval [-1.71, +4.82]). 404 collected questions, 403 valid questions graded per effort; one invalid reference annotation excluded symmetrically. The historical 202-question cross-model comparison below is unchanged. Study, timing and blind subjective results.

Preserved and documented by isilicon / Mango. The original model, modification and quantization remain the upstream creators' work. This repository adds attributed preservation and exact-configuration evaluation, with the selected source bytes unchanged.

At a glance

GB is decimal and GiB is binary. Payload size is disk/storage size, not a claim that the model fits in the same amount of VRAM. Runtime, KV cache, working memory and companions add their own requirements.

Mango evaluation

No standalone Mango quality score has been published for these exact files. This candidate is preserved, but its completed matched grade is not part of this card release.

A completed score requires a native preflight, matching frozen prompts, 202 suite answers, 12 agent cases, archive verification and the same reference graders. The benchmark methodology describes the protocol; publisher-side results are retained separately below.

Runtime and compatibility

Requires an architecture-compatible llama.cpp build and the correct source template. Mango's native specialist preflight and full matched comparison are separate from preserving the files.

No completed Mango full-suite or sandbox benchmark is published for these exact files.

The local evaluation covers text/tool tasks. It does not establish the full advertised context ceiling, image/audio quality or every optional speculative-decoding path. Publisher capabilities and Mango-verified behavior are separate scopes.

Companion artifacts

No separate companion mirror is declared in this selected manifest. This does not imply that every optional upstream projector, draft head or multimodal path is included; consult the exact file list.

Files and integrity

Full paths, byte sizes and complete SHA-256/Git blob identities are in SOURCE_MANIFEST.json. Available original README/license/notice files are also preserved. MIRROR_STATUS.json records the earlier source-file verification; MODEL_CARD_STATUS.json records this documentation refresh separately.

Download and use

The commands pin the already-verified mirror weight revision. Documentation can advance on main without changing that preserved weight snapshot. Keep original subfolders and all shards.

python -m pip install -U huggingface_hub

hf download isilicon/mango-cyberstrike-offsec-35b-q5k \
  Huihui-CyberStrike-OffSec-35B-abliterated-Q5_K.gguf \
  --revision 21e0aa060fc0729499717934f59dffe4c1a017f4 \
  --local-dir ./weights/cyberstrike-offsec-35b-q5k

Load example and setup scope

llama-server \
  --model ./weights/cyberstrike-offsec-35b-q5k/Huihui-CyberStrike-OffSec-35B-abliterated-Q5_K.gguf \
  --host 127.0.0.1 --port 8080 --ctx-size 32768 \
  --jinja --flash-attn on --cache-type-k q8_0 --cache-type-v q8_0

This is a load-command pattern, not a validated Mango inference or performance result for this candidate. Check architecture support before loading; enable projector/MTP options only after their own preflight.

Provenance and license

The publisher credits oyildirim/CyberStrike-OffSec-35B as the base and describes the modification as a proof-of-concept abliteration. The specialist label is provenance, not an independently measured Mango capability claim.

Original notices, base-model conditions and the publisher's stated limitations still apply. Downloadable preservation does not add new license rights. Source-described refusal modification and publisher-side benchmark claims have not been independently re-measured by this Mango task cohort.

Original publisher documentation

The unchanged upstream README and pinned source card retain the original usage guidance, technical discussion, attribution, caveats and citations.

Read the complete original publisher card

Source reference. The following is the original publisher's documentation. Its other quants, full-model files, context claims and benchmark tables can exceed the selection in this mirror. Relative asset/file URLs are qualified to the pinned original source; publisher measurements remain separate from Mango measurements.

huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated-GGUF

This is an uncensored version of oyildirim/CyberStrike-OffSec-35B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

llama.cpp

Use the latest llama.cpp,

llama-cli -m huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated-GGUF/Huihui-CyberStrike-OffSec-35B-abliterated-Q4_K.gguf -c 262144

Usage Warnings

• Risk of Sensitive or Controversial Outputs: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.

• Not Suitable for All Audiences: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.

• Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.

• Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.

• Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.

• No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.

Donation

Your donation helps us continue our further development and improvement, a cup of coffee can do it.

• bitcoin:

  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge

• Support our work on Ko-fi!

Preservation record

Selected source bytes are verified against pinned metadata; the original eight graded mirrors also passed the previously recorded anonymous 1 MiB weight-prefix checks. This is not a full independent-device restore/load test. Hugging Face repository copies share a provider and do not guarantee permanent storage.

Collection · Source manifest · Original documentation