Instructions to use wangzhang/gpt-oss-20b-abliterated-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wangzhang/gpt-oss-20b-abliterated-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="wangzhang/gpt-oss-20b-abliterated-GGUF",
	filename="gpt-oss-20b-abliterated-bf16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use wangzhang/gpt-oss-20b-abliterated-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M

Use Docker

docker model run hf.co/wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use wangzhang/gpt-oss-20b-abliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wangzhang/gpt-oss-20b-abliterated-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wangzhang/gpt-oss-20b-abliterated-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M

Ollama
How to use wangzhang/gpt-oss-20b-abliterated-GGUF with Ollama:
```
ollama run hf.co/wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M
```

Unsloth Studio

How to use wangzhang/gpt-oss-20b-abliterated-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for wangzhang/gpt-oss-20b-abliterated-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for wangzhang/gpt-oss-20b-abliterated-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open /spaces/unsloth/studio in your browser
# Search for wangzhang/gpt-oss-20b-abliterated-GGUF to start chatting

How to use wangzhang/gpt-oss-20b-abliterated-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use wangzhang/gpt-oss-20b-abliterated-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use wangzhang/gpt-oss-20b-abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M
```

Lemonade

How to use wangzhang/gpt-oss-20b-abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gpt-oss-20b-abliterated-GGUF-Q4_K_M

List all available models

lemonade list

gpt-oss-20b-abliterated — GGUF quants

GGUF builds of wangzhang/gpt-oss-20b-abliterated for running in llama.cpp, Ollama, LM Studio, KoboldCpp, text-generation-webui, and anything else that speaks GGUF.

Files

File	Quant	Size	Use case
`gpt-oss-20b-abliterated-bf16.gguf`	BF16 (full precision)	~42 GB	Reference quality. Requires 48+ GB VRAM (or large CPU RAM). Use if you care about identical behaviour to the HF checkpoint.
`gpt-oss-20b-abliterated-q8_0.gguf`	Q8_0 (8-bit, GGUF's FP8-equivalent)	~22 GB	Near-lossless vs BF16. Runs comfortably on a single 24 GB GPU. Recommended default.
`gpt-oss-20b-abliterated-q4_k_m.gguf`	Q4_K_M (4-bit k-quant, M profile)	~15 GB	Best size / quality trade-off at 4-bit. Fits on 16 GB VRAM or modest CPU setups.

GGUF does not have a native FP8 type; Q8_0 is the standard 8-bit path and is what every publisher on the Hub ships as "fp8 equivalent". Q4_K_M is the best 4-bit choice for this model — Q4_0 is noticeably worse on MoE models, Q5_K_M is ~25% larger for diminishing returns.

Source

Built from the merged BF16 weights of the abliteration run, not from the original MXFP4 (since the abliteration required dequantising experts to BF16 to enable direct weight editing). The BF16 → GGUF conversion uses llama.cpp's convert_hf_to_gguf.py; the quantised variants use llama-quantize.

All three files are functionally identical to the BF16 HF checkpoint at Q8_0 fidelity; Q4_K_M adds minor additional quantisation noise but keeps the abliteration effect intact (spot-checked on the same 15-prompt EN/ZH jailbreak set used for the HF release).

Quick start (llama.cpp)

# Download one quant:
huggingface-cli download wangzhang/gpt-oss-20b-abliterated-GGUF \
    gpt-oss-20b-abliterated-q4_k_m.gguf --local-dir ./

# Run with gpt-oss's harmony chat template (bundled in the GGUF):
./llama-cli -m gpt-oss-20b-abliterated-q4_k_m.gguf \
    -cnv -p "You are a helpful assistant." \
    --reasoning-budget 0 \
    -n 512

Quick start (Ollama)

ollama pull hf.co/wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M
ollama run hf.co/wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M

What this actually is

The HF checkpoint this is built from is an "abliterated" variant of gpt-oss-20b — refusals on harmful prompts have been suppressed via direct weight editing and MoE router suppression. Refusal rate on a 100-prompt held-out eval drops from 97/100 (base) to 6/100 (abliterated). See the base HF card for metrics, method, and honest limitations.

These GGUFs inherit that behaviour. They are intended for authorised AI-safety research, red-teaming, and mechanism analysis — not for producing or distributing harmful content. The apache-2.0 license of the upstream OpenAI gpt-oss release applies.

Acknowledgments

openai/gpt-oss-20b — base model
ggerganov/llama.cpp — GGUF format and quantisation kernels
abliterix — abliteration pipeline (Heretic derivative)

Downloads last month: 408

GGUF

Model size

21B params

Architecture

gpt-oss

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for wangzhang/gpt-oss-20b-abliterated-GGUF

Base model

openai/gpt-oss-20b

Finetuned

wangzhang/gpt-oss-20b-abliterated

Quantized

(3)

this model

Collection including wangzhang/gpt-oss-20b-abliterated-GGUF

GPT-Abliterated

Collection

3 items • Updated 18 days ago • 1