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
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model. 

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/NINI26454%2FOpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Q3_K_M-GGUF"
Response includes
  • classification m3
  • files 4
  • hub_downloads_all_time 481
  • author_summary 16 models
  • readme_text full
Try next
GET/models?author=NINI26454
All 16 models by NINI26454
 GET/methods/m3
What "m3" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
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
481
197 last 30d - stable
Likes
0
Model age
6w ago
created 2026-09-11
Downloads over time
Now675→from0↑0%
02484957430 on Sep 11675 on Oct 29SepOct
Sep 11 → Oct 29 · 49 snapshots · spans 48 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↓ 25,904 this lineage
NINI26454/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Q3_K_M-GGUF↓ 197

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
Mistral-Small-24B-Instruct-2501-Abliterated-GGUF 256 Huihui-Qwen3.6-27B-abliterated-MTP-Q3_K-GGUF 170 gemma-2-9b-it-Abliterated-GGUF 149 Qwen2.5-Coder-14B-Instruct-Abliterated-GGUF 108 Qwen2.5-Coder-7B-Instruct-Abliterated-GGUF 87
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 Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration