Architecture: nemotron_h_moe (requires llama.cpp build b10326+)
Quantization: Q8_0
File size: 33.6 GB
Smoke-tested locally before upload (loads + coherent output on llama-cli).

Results

Refusals	Compliance	KL Divergence	Trials
0%	100%	0.0397	200

Independent eval of the merged BF16 model (50 harmful-behavior prompts). The automated Zou keyword detector false-positives on words like "illegal"/"unethical" appearing inside compliant answers; manual review found 0 genuine refusals.

Usage

bash

llama-cli -m Nemotron-3.5-Lightning-30B-A3B-Heretic-Uncensored-Q8_0-GGUF.gguf \
  -cnv -st -p "What is 2+2?"

Ollama

Create a Modelfile:

FROM ./Nemotron-3.5-Lightning-30B-A3B-Heretic-Uncensored-Q8_0-GGUF.gguf

Then:

bash

ollama create nemotron-3.5-30b-heretic-q8_0
ollama run nemotron-3.5-30b-heretic-q8_0

Abliteration removes safety alignment. Use responsibly and in accordance with your local laws and the upstream NVIDIA Open Model License.

mlasli/Nemotron-3.5-Lightning-30B-A3B-Heretic-Uncensored-Q8_0-GGUF

Nemotron-3.5-Lightning-30B-A3B Heretic-Abliterated (Q8_0 GGUF)

Results

Usage

Ollama

mlasli/
Nemotron-3.5-Lightning-30B-A3B-Heretic-Uncensored-Q8_0-GGUF