base_model:
- llmfan46/Dark-Nexus-27B-v3.0-uncensored-heretic
tags: - qwen3_5
- nsfw
- explicit
- roleplay
- unaligned
- dangerous
- ERP
- Other License
- heretic
- uncensored
- decensored
- abliterated
- ara
license: other
🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨
I can no longer upload new models unless I can cover the cost of additional storage.
I host 70+ free models as an independent contributor and this work is unpaid.
Without your support, no more new models can be uploaded.
🎉 Patreon (Monthly) | ☕ Ko-fi (One-time)
Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone.
88% fewer refusals (10/100 Uncensored vs 84/100 Original) while preserving model quality (0.0883 KL divergence).
❤️ Support My Work
Creating these models takes significant time, work and compute. If you find them useful consider supporting me:
| Platform | Link | What you get |
|---|---|---|
| 🎉 Patreon | Monthly support | Priority model requests |
| ☕ Ko-fi | One-time tip | My eternal gratitude |
Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.
GGUF quantizations of llmfan46/Dark-Nexus-27B-v3.0-uncensored-heretic.
This is a decensored version of ReadyArt/Dark-Nexus-27B-v3.0, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method
Abliteration parameters
| Parameter | Value |
|---|---|
| start_layer_index | 4 |
| end_layer_index | 43 |
| preserve_good_behavior_weight | 0.0666 |
| steer_bad_behavior_weight | 0.0002 |
| overcorrect_relative_weight | 1.0488 |
| neighbor_count | 11 |
Targeted components
- attn.o_proj
- attn.out_proj
Performance
| Metric | This model | Original model (ReadyArt/Dark-Nexus-27B-v3.0) |
|---|---|---|
| KL divergence | 0.0883 | 0 (by definition) |
| Refusals | ✅ 10/100 | ❌ 84/100 |
Lower refusals indicate fewer content restrictions, while lower KL divergence indicates more closeness to the original model's baseline. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections.
MMLU test results:
Original:
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| mmlu | 2 | none | acc | ↑ | 0.8532 | ± | 0.0029 | |
| - humanities | 2 | none | acc | ↑ | 0.8019 | ± | 0.0056 | |
| - formal_logic | 1 | none | 0 | acc | ↑ | 0.7381 | ± | 0.0393 |
| - high_school_european_history | 1 | none | 0 | acc | ↑ | 0.8848 | ± | 0.0249 |
| - high_school_us_history | 1 | none | 0 | acc | ↑ | 0.9461 | ± | 0.0159 |
| - high_school_world_history | 1 | none | 0 | acc | ↑ | 0.9578 | ± | 0.0131 |
| - international_law | 1 | none | 0 | acc | ↑ | 0.9256 | ± | 0.0240 |
| - jurisprudence | 1 | none | 0 | acc | ↑ | 0.9259 | ± | 0.0253 |
| - logical_fallacies | 1 | none | 0 | acc | ↑ | 0.8834 | ± | 0.0252 |
| - moral_disputes | 1 | none | 0 | acc | ↑ | 0.8728 | ± | 0.0179 |
| - moral_scenarios | 1 | none | 0 | acc | ↑ | 0.7073 | ± | 0.0152 |
| - philosophy | 1 | none | 0 | acc | ↑ | 0.8746 | ± | 0.0188 |
| - prehistory | 1 | none | 0 | acc | ↑ | 0.9105 | ± | 0.0159 |
| - professional_law | 1 | none | 0 | acc | ↑ | 0.7158 | ± | 0.0115 |
| - world_religions | 1 | none | 0 | acc | ↑ | 0.9240 | ± | 0.0203 |
| - other | 2 | none | acc | ↑ | 0.8742 | ± | 0.0057 | |
| - business_ethics | 1 | none | 0 | acc | ↑ | 0.8300 | ± | 0.0378 |
| - clinical_knowledge | 1 | none | 0 | acc | ↑ | 0.9057 | ± | 0.0180 |
| - college_medicine | 1 | none | 0 | acc | ↑ | 0.8728 | ± | 0.0254 |
| - global_facts | 1 | none | 0 | acc | ↑ | 0.6000 | ± | 0.0492 |
| - human_aging | 1 | none | 0 | acc | ↑ | 0.8520 | ± | 0.0238 |
| - management | 1 | none | 0 | acc | ↑ | 0.8835 | ± | 0.0318 |
| - marketing | 1 | none | 0 | acc | ↑ | 0.9487 | ± | 0.0145 |
| - medical_genetics | 1 | none | 0 | acc | ↑ | 0.9500 | ± | 0.0219 |
| - miscellaneous | 1 | none | 0 | acc | ↑ | 0.9323 | ± | 0.0090 |
| - nutrition | 1 | none | 0 | acc | ↑ | 0.8987 | ± | 0.0173 |
| - professional_accounting | 1 | none | 0 | acc | ↑ | 0.8014 | ± | 0.0238 |
| - professional_medicine | 1 | none | 0 | acc | ↑ | 0.9559 | ± | 0.0125 |
| - virology | 1 | none | 0 | acc | ↑ | 0.5602 | ± | 0.0386 |
| - social sciences | 2 | none | acc | ↑ | 0.9110 | ± | 0.0050 | |
| - econometrics | 1 | none | 0 | acc | ↑ | 0.7982 | ± | 0.0378 |
| - high_school_geography | 1 | none | 0 | acc | ↑ | 0.9343 | ± | 0.0176 |
| - high_school_government_and_politics | 1 | none | 0 | acc | ↑ | 0.9896 | ± | 0.0073 |
| - high_school_macroeconomics | 1 | none | 0 | acc | ↑ | 0.9333 | ± | 0.0126 |
| - high_school_microeconomics | 1 | none | 0 | acc | ↑ | 0.9538 | ± | 0.0136 |
| - high_school_psychology | 1 | none | 0 | acc | ↑ | 0.9560 | ± | 0.0088 |
| - human_sexuality | 1 | none | 0 | acc | ↑ | 0.9237 | ± | 0.0233 |
| - professional_psychology | 1 | none | 0 | acc | ↑ | 0.8824 | ± | 0.0130 |
| - public_relations | 1 | none | 0 | acc | ↑ | 0.7727 | ± | 0.0401 |
| - security_studies | 1 | none | 0 | acc | ↑ | 0.8041 | ± | 0.0254 |
| - sociology | 1 | none | 0 | acc | ↑ | 0.9254 | ± | 0.0186 |
| - us_foreign_policy | 1 | none | 0 | acc | ↑ | 0.9500 | ± | 0.0219 |
| - stem | 2 | none | acc | ↑ | 0.8525 | ± | 0.0061 | |
| - abstract_algebra | 1 | none | 0 | acc | ↑ | 0.7800 | ± | 0.0416 |
| - anatomy | 1 | none | 0 | acc | ↑ | 0.8593 | ± | 0.0300 |
| - astronomy | 1 | none | 0 | acc | ↑ | 0.9539 | ± | 0.0171 |
| - college_biology | 1 | none | 0 | acc | ↑ | 0.9653 | ± | 0.0153 |
| - college_chemistry | 1 | none | 0 | acc | ↑ | 0.6700 | ± | 0.0473 |
| - college_computer_science | 1 | none | 0 | acc | ↑ | 0.8300 | ± | 0.0378 |
| - college_mathematics | 1 | none | 0 | acc | ↑ | 0.7100 | ± | 0.0456 |
| - college_physics | 1 | none | 0 | acc | ↑ | 0.7745 | ± | 0.0416 |
| - computer_security | 1 | none | 0 | acc | ↑ | 0.8400 | ± | 0.0368 |
| - conceptual_physics | 1 | none | 0 | acc | ↑ | 0.9277 | ± | 0.0169 |
| - electrical_engineering | 1 | none | 0 | acc | ↑ | 0.8345 | ± | 0.0310 |
| - elementary_mathematics | 1 | none | 0 | acc | ↑ | 0.8995 | ± | 0.0155 |
| - high_school_biology | 1 | none | 0 | acc | ↑ | 0.9613 | ± | 0.0110 |
| - high_school_chemistry | 1 | none | 0 | acc | ↑ | 0.8522 | ± | 0.0250 |
| - high_school_computer_science | 1 | none | 0 | acc | ↑ | 0.9300 | ± | 0.0256 |
| - high_school_mathematics | 1 | none | 0 | acc | ↑ | 0.6778 | ± | 0.0285 |
| - high_school_physics | 1 | none | 0 | acc | ↑ | 0.8411 | ± | 0.0299 |
| - high_school_statistics | 1 | none | 0 | acc | ↑ | 0.8750 | ± | 0.0226 |
| - machine_learning | 1 | none | 0 | acc | ↑ | 0.7500 | ± | 0.0411 |
| Groups | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| mmlu | 2 | none | acc | ↑ | 0.8532 | ± | 0.0029 | |
| - humanities | 2 | none | acc | ↑ | 0.8019 | ± | 0.0056 | |
| - other | 2 | none | acc | ↑ | 0.8742 | ± | 0.0057 | |
| - social sciences | 2 | none | acc | ↑ | 0.9110 | ± | 0.0050 | |
| - stem | 2 | none | acc | ↑ | 0.8525 | ± | 0.0061 |
Heretic:
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| mmlu | 2 | none | acc | ↑ | 0.8455 | ± | 0.0029 | |
| - humanities | 2 | none | acc | ↑ | 0.7796 | ± | 0.0058 | |
| - formal_logic | 1 | none | 0 | acc | ↑ | 0.7381 | ± | 0.0393 |
| - high_school_european_history | 1 | none | 0 | acc | ↑ | 0.8909 | ± | 0.0243 |
| - high_school_us_history | 1 | none | 0 | acc | ↑ | 0.9510 | ± | 0.0152 |
| - high_school_world_history | 1 | none | 0 | acc | ↑ | 0.9409 | ± | 0.0153 |
| - international_law | 1 | none | 0 | acc | ↑ | 0.9256 | ± | 0.0240 |
| - jurisprudence | 1 | none | 0 | acc | ↑ | 0.9259 | ± | 0.0253 |
| - logical_fallacies | 1 | none | 0 | acc | ↑ | 0.9018 | ± | 0.0234 |
| - moral_disputes | 1 | none | 0 | acc | ↑ | 0.8584 | ± | 0.0188 |
| - moral_scenarios | 1 | none | 0 | acc | ↑ | 0.6223 | ± | 0.0162 |
| - philosophy | 1 | none | 0 | acc | ↑ | 0.8842 | ± | 0.0182 |
| - prehistory | 1 | none | 0 | acc | ↑ | 0.9167 | ± | 0.0154 |
| - professional_law | 1 | none | 0 | acc | ↑ | 0.6962 | ± | 0.0117 |
| - world_religions | 1 | none | 0 | acc | ↑ | 0.9240 | ± | 0.0203 |
| - other | 2 | none | acc | ↑ | 0.8719 | ± | 0.0057 | |
| - business_ethics | 1 | none | 0 | acc | ↑ | 0.8300 | ± | 0.0378 |
| - clinical_knowledge | 1 | none | 0 | acc | ↑ | 0.9170 | ± | 0.0170 |
| - college_medicine | 1 | none | 0 | acc | ↑ | 0.8671 | ± | 0.0259 |
| - global_facts | 1 | none | 0 | acc | ↑ | 0.5800 | ± | 0.0496 |
| - human_aging | 1 | none | 0 | acc | ↑ | 0.8430 | ± | 0.0244 |
| - management | 1 | none | 0 | acc | ↑ | 0.8932 | ± | 0.0306 |
| - marketing | 1 | none | 0 | acc | ↑ | 0.9444 | ± | 0.0150 |
| - medical_genetics | 1 | none | 0 | acc | ↑ | 0.9500 | ± | 0.0219 |
| - miscellaneous | 1 | none | 0 | acc | ↑ | 0.9336 | ± | 0.0089 |
| - nutrition | 1 | none | 0 | acc | ↑ | 0.9052 | ± | 0.0168 |
| - professional_accounting | 1 | none | 0 | acc | ↑ | 0.7801 | ± | 0.0247 |
| - professional_medicine | 1 | none | 0 | acc | ↑ | 0.9559 | ± | 0.0125 |
| - virology | 1 | none | 0 | acc | ↑ | 0.5482 | ± | 0.0387 |
| - social sciences | 2 | none | acc | ↑ | 0.9116 | ± | 0.0050 | |
| - econometrics | 1 | none | 0 | acc | ↑ | 0.7982 | ± | 0.0378 |
| - high_school_geography | 1 | none | 0 | acc | ↑ | 0.9394 | ± | 0.0170 |
| - high_school_government_and_politics | 1 | none | 0 | acc | ↑ | 0.9896 | ± | 0.0073 |
| - high_school_macroeconomics | 1 | none | 0 | acc | ↑ | 0.9282 | ± | 0.0131 |
| - high_school_microeconomics | 1 | none | 0 | acc | ↑ | 0.9664 | ± | 0.0117 |
| - high_school_psychology | 1 | none | 0 | acc | ↑ | 0.9523 | ± | 0.0091 |
| - human_sexuality | 1 | none | 0 | acc | ↑ | 0.9160 | ± | 0.0243 |
| - professional_psychology | 1 | none | 0 | acc | ↑ | 0.8840 | ± | 0.0130 |
| - public_relations | 1 | none | 0 | acc | ↑ | 0.7636 | ± | 0.0407 |
| - security_studies | 1 | none | 0 | acc | ↑ | 0.8163 | ± | 0.0248 |
| - sociology | 1 | none | 0 | acc | ↑ | 0.9303 | ± | 0.0180 |
| - us_foreign_policy | 1 | none | 0 | acc | ↑ | 0.9400 | ± | 0.0239 |
| - stem | 2 | none | acc | ↑ | 0.8532 | ± | 0.0061 | |
| - abstract_algebra | 1 | none | 0 | acc | ↑ | 0.7600 | ± | 0.0429 |
| - anatomy | 1 | none | 0 | acc | ↑ | 0.8593 | ± | 0.0300 |
| - astronomy | 1 | none | 0 | acc | ↑ | 0.9539 | ± | 0.0171 |
| - college_biology | 1 | none | 0 | acc | ↑ | 0.9653 | ± | 0.0153 |
| - college_chemistry | 1 | none | 0 | acc | ↑ | 0.6700 | ± | 0.0473 |
| - college_computer_science | 1 | none | 0 | acc | ↑ | 0.8300 | ± | 0.0378 |
| - college_mathematics | 1 | none | 0 | acc | ↑ | 0.7300 | ± | 0.0446 |
| - college_physics | 1 | none | 0 | acc | ↑ | 0.7843 | ± | 0.0409 |
| - computer_security | 1 | none | 0 | acc | ↑ | 0.8400 | ± | 0.0368 |
| - conceptual_physics | 1 | none | 0 | acc | ↑ | 0.9362 | ± | 0.0160 |
| - electrical_engineering | 1 | none | 0 | acc | ↑ | 0.8207 | ± | 0.0320 |
| - elementary_mathematics | 1 | none | 0 | acc | ↑ | 0.8915 | ± | 0.0160 |
| - high_school_biology | 1 | none | 0 | acc | ↑ | 0.9677 | ± | 0.0101 |
| - high_school_chemistry | 1 | none | 0 | acc | ↑ | 0.8424 | ± | 0.0256 |
| - high_school_computer_science | 1 | none | 0 | acc | ↑ | 0.9300 | ± | 0.0256 |
| - high_school_mathematics | 1 | none | 0 | acc | ↑ | 0.6778 | ± | 0.0285 |
| - high_school_physics | 1 | none | 0 | acc | ↑ | 0.8543 | ± | 0.0288 |
| - high_school_statistics | 1 | none | 0 | acc | ↑ | 0.8704 | ± | 0.0229 |
| - machine_learning | 1 | none | 0 | acc | ↑ | 0.7768 | ± | 0.0395 |
| Groups | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| mmlu | 2 | none | acc | ↑ | 0.8455 | ± | 0.0029 | |
| - humanities | 2 | none | acc | ↑ | 0.7796 | ± | 0.0058 | |
| - other | 2 | none | acc | ↑ | 0.8719 | ± | 0.0057 | |
| - social sciences | 2 | none | acc | ↑ | 0.9116 | ± | 0.0050 | |
| - stem | 2 | none | acc | ↑ | 0.8532 | ± | 0.0061 |
MMLU - Massive Multitask Language Understanding, multiple-choice questions across 57 subjects (math, history, law, medicine, etc.).
Quantizations
| Filename | Quant | Description |
|---|---|---|
| Dark-Nexus-27B-v3.0-uncensored-heretic-BF16.gguf | BF16 | Full precision |
| Dark-Nexus-27B-v3.0-uncensored-heretic-Q8_0.gguf | Q8_0 | Near-lossless, recommended |
| Dark-Nexus-27B-v3.0-uncensored-heretic-Q6_K.gguf | Q6_K | Excellent quality |
| Dark-Nexus-27B-v3.0-uncensored-heretic-Q5_K_M.gguf | Q5_K_M | Good balance |
| Dark-Nexus-27B-v3.0-uncensored-heretic-Q5_K_SQwen3.5-27B-ultra-uncensored-heretic-v2-v2-Q5_K_S.gguf | Q5_K_S | Smaller Q5 |
| Dark-Nexus-27B-v3.0-uncensored-heretic-Q4_K_M.gguf | Q4_K_M | Good for limited VRAM |
| Dark-Nexus-27B-v3.0-uncensored-heretic-Q4_K_S.gguf | Q4_K_S | Smaller Q4 |
| Dark-Nexus-27B-v3.0-uncensored-heretic-Q3_K_L.gguf | Q3_K_L | Low VRAM, decent quality |
| Dark-Nexus-27B-v3.0-uncensored-heretic-Q3_K_M.gguf | Q3_K_M | Low VRAM, smaller |
Vision Projector
| Filename | Quant | Description |
|---|---|---|
| Dark-Nexus-27B-v3.0-mmproj-BF16.gguf | BF16 | Native precision |
A Vision Projector File is Required for vision/multimodal capabilities. Use alongside any quantization above.
Usage
Works with llama.cpp, LM Studio, Ollama, and other GGUF-compatible tools.
Dark Nexus v3.0
27B
Total Damnation
🌑 Dark Evolution
This model doesn't just cross lines - it erases them with arterial spray:
- 🧬 Merged Dataset - The successor to Dark Desires, Darkness Incarnate, Dark Osmosis, Brisk Evolution, Tutu, For Her Darkside, Dark Oddity, Omega Darker and Omega Directive.
- 🧼 Cleaned Dataset - Dataset has been wiped of formatting issues. And has been deslopped (not fully, but enough). This has resulted in a large amount of the dataset being lost.
⚙️ Technical Specifications
This is a two epoch tune.
You'll need to play with sampler settings with this model.
GGUF
Quants☠️ Ethical Vacuum
This model operates in complete moral darkness:
- 🚫 No moral or ethical constraints on generated content
- 🔞 Will enthusiastically engage with any NSFW scenario
- 🖤 No psychological safety measures whatsoever
- 🔪 Will graphically depict any violent requested
🧑🔬 Creators
- FrenzyBiscuit (Fine-Tuning & Data Gen Tool & Several Datasets)
- Sleep Deprived (Safeword/Omega/Tutu Series & Data Gen Tool)
👨🏼🔬 Other Help
- ToastyPigeon (Base Model)
- GECFDO (Dataset Generation Contributor & Quants)
- Darkhn (Dataset Cleanup Tool)
- Dysfunctional (Model Card Image)
🔖 License
By using this model, you agree:
- This tune is based on the Apache 2.0 license
- To accept full responsibility for all generated content
- That you're at least 18+ years old
- That the architects bear no responsibility for your corruption
- This model is intended for personal usage only. Using this model for profit and/or for commerical use is not allowed to the extent legally permitted by the original license.