Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive
4BNemotronuncensored
from nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
↓ 5.1K♥ 375 repos
Nemotron-3.5-Lightning-30B-A3B-CRACK
Nemotron-3.5-Lightning-30B-A3B-CRACK is a abliterated and uncensored variant of nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16, published on Hugging Face by dealignai. It is 30B total parameters (mixture-of-experts), 48GB VRAM class class and other licence. It is distributed across 2 repositories in GGUF format, totalling 16.6K downloads.
Specification
- Model name
- Nemotron-3.5-Lightning-30B-A3B-CRACK
- Source repository
- dealignai/Nemotron-3.5-Lightning-30B-A3B-CRACK-GGUF
- Publisher
- dealignai
- Parameters
- 30B (mixture-of-experts)
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- other
- Task
- Text generation
- Context window
- 262K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 12 Aug 2026
- Last updated
- 12 Aug 2026
Ablation technique
How Nemotron-3.5-Lightning-30B-A3B-CRACK was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“CRACK-abliterated NVIDIA Nemotron 3.5 Lightning 30B-A3B — GGUF quants for llama.cpp. Three quantizations (Q80 / Q4KM / Q2K) in one repository, each with the native MTP (Multi-Token Prediction) draft head folded in for speculative decoding. Refusal behavior removed while preserving the model's knowledge, reasoning...”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download dealignai/Nemotron-3.5-Lightning-30B-A3B-CRACK-GGUF --local-dir ./nemotron-3.5-lightning-30b-a3b-crack
llama-cli -m ./nemotron-3.5-lightning-30b-a3b-crack/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "dealignai/Nemotron-3.5-Lightning-30B-A3B-CRACK-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve dealignai/Nemotron-3.5-Lightning-30B-A3B-CRACK-GGUF --trust-remote-codeDownloads and variants (1)
The only published repository of Nemotron-3.5-Lightning-30B-A3B-CRACK.
| Repository | Format | Downloads |
|---|---|---|
| dealignai/Nemotron-3.5-Lightning-30B-A3B-CRACK-GGUFsource | GGUF | 16.6K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Nemotron-3.5-Lightning-30B-A3B-CRACK will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- Capability is inherited from nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16, not added by ablation — at 30B parameters, expect roughly the base model’s competence, minus some instruction-following fidelity.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- Declared licence is other, but the terms that bind you are nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16’s — a re-release cannot grant more than its parent.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for Nemotron-3.5-Lightning-30B-A3B-CRACK is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with dealignai, and does not independently verify publisher claims. See responsible use.