Get the app
← back to catalog · registered 2026-09-11 18:55

NINI26454/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Q3_K_M-GGUF

NINI26454 20B GGUF second-order 131K ctx
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
M1 Direct removal →
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
How we label → About M3 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
178
Likes
0
Model age
2d ago
created 2026-09-11
Downloads over time
Now178→from0↑0%
0651311960 on Sep 11178 on Sep 14Sep
Sep 11 → Sep 14 · 4 snapshots · spans 3 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

DavidAU/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Imatrix-gguf↓ 24,647 this lineage
NINI26454/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Q3_K_M-GGUF↓ 178

Metadata

License
apache-2.0
Quantizations
Q3_K
Tags
gguf ollama openai gpt-oss uncensored 3bit base_model:DavidAU/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Imatrix-gguf base_model:quantized:DavidAU/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Imatrix-gguf license:apache-2.0 endpoints_compatible region:us imatrix

Related

Other by NINI26454
Qwen2.5-Coder-32B-Instruct-Abliterated-GGUF 234 Qwen2.5-Coder-7B-Instruct-Abliterated-GGUF 222 Qwen2.5-Coder-14B-Instruct-Abliterated-GGUF 201 Llama-3.1-8B-Instruct-Abliterated-GGUF 148 Huihui-CyberStrike-OffSec-35B-abliterated-GGUF 142
Total size
12.0 GB
Files
4
Quantizations
2
Registered
2026-09-11 18:55
Last updated on HF
2026-09-11 17:58
Source huggingface.co/NINI26454/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Q3_K_M-GGUF ↗ Base model DavidAU/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Imatrix-gguf →

Files by quantization

Q3_K 1 file 12.0 GB
OpenAI-20B-NEOPlus-Uncensored-Q3_K_M.gguf 12.0 GB 3c173e8a download
Auxiliary files 3 files 2.85 KB
.gitattributes 1.56 KB ea03846e download
README.md 958 B 401e90d3 download
Modelfile 363 B 8c43d726 download

README current version from Hugging Face

license: apache-2.0
base_model: DavidAU/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Imatrix-gguf
tags:

  • gguf
  • ollama
  • openai
  • gpt-oss
  • uncensored
  • 3bit

OpenAI-GPT-oss-20B-HERETIC-NEO-Q3_K_M-GGUF

3-bit GGUF quantization of DavidAU/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Imatrix-gguf.

Included Files

  • OpenAI-20B-NEOPlus-Uncensored-Q3_K_M.gguf (3-bit medium quantization, 12.3 GB)
  • Modelfile (Ready-to-use Ollama Modelfile)

How to Run with Ollama

  1. Download both the .gguf and Modelfile to the same folder.
  2. Run:
ollama create gpt-oss-20b-neo -f Modelfile
ollama run gpt-oss-20b-neo

How to Run with llama.cpp

llama-cli -m OpenAI-20B-NEOPlus-Uncensored-Q3_K_M.gguf -p "Hello, can you help me write a Python script?" -c 8192

EOF
ls -lh /teamspace/studios/this_studio/models/export_gpt_oss_20b/

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-09-11Upload folder using huggingface_hub414bf66958 B
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.

See supported apps Browse the catalog