Instructions to use DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1
# Run inference directly in the terminal:
llama cli -hf DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1
# Run inference directly in the terminal:
llama cli -hf DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1

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 DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1
# Run inference directly in the terminal:
./llama-cli -hf DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1

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 DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1

Use Docker

docker model run hf.co/DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1

LM Studio
Jan

vLLM

How to use DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-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": "DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1

Ollama
How to use DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf with Ollama:
```
ollama run hf.co/DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1
```

Unsloth Studio

How to use DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-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 DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-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 DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf to start chatting

How to use DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1

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": "DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1

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 DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf with Docker Model Runner:
```
docker model run hf.co/DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1
```

Lemonade

How to use DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf:Q5_1

Run and chat with the model

lemonade run user.OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf-Q5_1

List all available models

lemonade list

Model won't load ollama on open ui

by N0torius - opened Aug 8, 2025

Discussion

N0torius

Aug 8, 2025

•

edited Aug 22, 2025

I get error 500: unable to load model
Think i had this when oss first came out but i hadn't updated ollama

Edit: fixed as of 11.5 i think

Pitufin

Aug 8, 2025

I get the same error with Ollama 0.11.4: Error: 500 Internal Server Error: unable to load model.

cyberax

Aug 8, 2025

yes the version given in the model and "gpt-oss" and ollama wants to see "gptoss"

N0torius

Aug 8, 2025

yes the version given in the model and "gpt-oss" and ollama wants to see "gptoss"

Can I fix this myself? I don't know a whole lot about this type of thing it was hard enough getting ollama working with my gpu. Haha

cyberax

Aug 10, 2025

The term gpt-oss is written directly into the guff file. It can't be modified like that in gptoss because that would change the address of all internal data.

I modified ollama to access both, but then another error occurred because llama.cpp doesn't accept the new compression yet. I have to wait for llama.cpp to release an update.

randomStudent

Aug 10, 2025

So it has the command to run in Ollama, but it won't work? I've been trying for days to get rid of this 500 server error. My computer runs the official oss-20b, but it won't run any of the uncensored ones through Ollama. How did the creator make it for ollama if it doesn't work? Sorry, Im not an expert in the backend of ai's yet.

Pitufin

Aug 11, 2025

•

edited Aug 11, 2025

As far as I know, this is due to a llama.cpp version dependence not satisfied in Ollama yet. This requisite is generated from the original abliterated version.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment