Instructions to use llmfan46/gpt-oss-120b-ultra-heretic-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmfan46/gpt-oss-120b-ultra-heretic-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmfan46/gpt-oss-120b-ultra-heretic-GGUF",
	filename="gpt-oss-120b-heretic-ultra-heretic-MXFP4.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 llmfan46/gpt-oss-120b-ultra-heretic-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmfan46/gpt-oss-120b-ultra-heretic-GGUF
# Run inference directly in the terminal:
llama-cli -hf llmfan46/gpt-oss-120b-ultra-heretic-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmfan46/gpt-oss-120b-ultra-heretic-GGUF
# Run inference directly in the terminal:
llama-cli -hf llmfan46/gpt-oss-120b-ultra-heretic-GGUF

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 llmfan46/gpt-oss-120b-ultra-heretic-GGUF
# Run inference directly in the terminal:
./llama-cli -hf llmfan46/gpt-oss-120b-ultra-heretic-GGUF

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 llmfan46/gpt-oss-120b-ultra-heretic-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmfan46/gpt-oss-120b-ultra-heretic-GGUF

Use Docker

docker model run hf.co/llmfan46/gpt-oss-120b-ultra-heretic-GGUF

LM Studio
Jan

vLLM

How to use llmfan46/gpt-oss-120b-ultra-heretic-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmfan46/gpt-oss-120b-ultra-heretic-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": "llmfan46/gpt-oss-120b-ultra-heretic-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llmfan46/gpt-oss-120b-ultra-heretic-GGUF

Ollama
How to use llmfan46/gpt-oss-120b-ultra-heretic-GGUF with Ollama:
```
ollama run hf.co/llmfan46/gpt-oss-120b-ultra-heretic-GGUF
```

Unsloth Studio

How to use llmfan46/gpt-oss-120b-ultra-heretic-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 llmfan46/gpt-oss-120b-ultra-heretic-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 llmfan46/gpt-oss-120b-ultra-heretic-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for llmfan46/gpt-oss-120b-ultra-heretic-GGUF to start chatting

How to use llmfan46/gpt-oss-120b-ultra-heretic-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf llmfan46/gpt-oss-120b-ultra-heretic-GGUF

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": "llmfan46/gpt-oss-120b-ultra-heretic-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use llmfan46/gpt-oss-120b-ultra-heretic-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 llmfan46/gpt-oss-120b-ultra-heretic-GGUF

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 llmfan46/gpt-oss-120b-ultra-heretic-GGUF

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use llmfan46/gpt-oss-120b-ultra-heretic-GGUF with Docker Model Runner:
```
docker model run hf.co/llmfan46/gpt-oss-120b-ultra-heretic-GGUF
```

Lemonade

How to use llmfan46/gpt-oss-120b-ultra-heretic-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmfan46/gpt-oss-120b-ultra-heretic-GGUF

Run and chat with the model

lemonade run user.gpt-oss-120b-ultra-heretic-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨

I can no longer upload new models unless I can cover the cost of additional storage.
I host 70+ free models as an independent contributor and this work is unpaid.
Without your support, no more new models can be uploaded.

🎉 Patreon (Monthly) | ☕ Ko-fi (One-time)

Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone.

gpt-oss-120b-ultra-heretic-GGUF

GGUF quantizations of llmfan46/gpt-oss-120b-ultra-heretic.

This is a decensored version of openai/gpt-oss-120b, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method

Abliteration parameters

Parameter	Value
start_layer_index	15
end_layer_index	32
preserve_good_behavior_weight	0.3968
steer_bad_behavior_weight	0.0990
overcorrect_relative_weight	0.9882
neighbor_count	8

Performance

Metric	This model	Original model (gpt-oss-120b)
KL divergence	0.0703	0 (by definition)
Refusals	3/100	98/100

Lower refusals indicate fewer content restrictions, while lower KL divergence indicates better preservation of the original model's capabilities. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections, while higher KL divergence degrades coherence, reasoning ability, and overall quality.

Quantizations

Filename	Quant	Description
gpt-oss-120b-heretic-ultra-heretic-BF16.gguf	BF16	Full precision
gpt-oss-120b-heretic-ultra-heretic-Q8_0.gguf	Q8_0	Near-lossless
gpt-oss-120b-heretic-ultra-heretic-Q5_K_M.gguf	Q5_K_M	Quality
gpt-oss-120b-heretic-ultra-heretic-Q5_K_S.gguf	Q5_K_S	Balanced
gpt-oss-120b-heretic-ultra-heretic-Q4_K_S.gguf	Q4_K_S	Budget
gpt-oss-120b-heretic-ultra-heretic-Q3_K_L.gguf	Q3_K_L	Low VRAM
gpt-oss-120b-heretic-ultra-heretic-MXFP4.gguf	MXFP4	Smallest, original 4-bit format

Usage

Works with llama.cpp, LM Studio, Ollama, and other GGUF-compatible tools.

gpt-oss-120b

Try gpt-oss · Guides · Model card · OpenAI blog

Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.

We’re releasing two flavors of these open models:

gpt-oss-120b — for production, general purpose, high reasoning use cases that fit into a single 80GB GPU (like NVIDIA H100 or AMD MI300X) (117B parameters with 5.1B active parameters)
gpt-oss-20b — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)

Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.

This model card is dedicated to the larger gpt-oss-120b model. Check out gpt-oss-20b for the smaller model.

Highlights

Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
Full chain-of-thought: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.
Fine-tunable: Fully customize models to your specific use case through parameter fine-tuning.
Agentic capabilities: Use the models’ native capabilities for function calling, web browsing, Python code execution, and Structured Outputs.
MXFP4 quantization: The models were post-trained with MXFP4 quantization of the MoE weights, making gpt-oss-120b run on a single 80GB GPU (like NVIDIA H100 or AMD MI300X) and the gpt-oss-20b model run within 16GB of memory. All evals were performed with the same MXFP4 quantization.

Inference examples

Transformers

You can use gpt-oss-120b and gpt-oss-20b with Transformers. If you use the Transformers chat template, it will automatically apply the harmony response format. If you use model.generate directly, you need to apply the harmony format manually using the chat template or use our openai-harmony package.

To get started, install the necessary dependencies to setup your environment:

pip install -U transformers kernels torch

Once, setup you can proceed to run the model by running the snippet below:

from transformers import pipeline
import torch

model_id = "openai/gpt-oss-120b"

pipe = pipeline(
    "text-generation",
    model=model_id,
    torch_dtype="auto",
    device_map="auto",
)

messages = [
    {"role": "user", "content": "Explain quantum mechanics clearly and concisely."},
]

outputs = pipe(
    messages,
    max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])

Alternatively, you can run the model via Transformers Serve to spin up a OpenAI-compatible webserver:

transformers serve
transformers chat localhost:8000 --model-name-or-path openai/gpt-oss-120b

Learn more about how to use gpt-oss with Transformers.

vLLM

vLLM recommends using uv for Python dependency management. You can use vLLM to spin up an OpenAI-compatible webserver. The following command will automatically download the model and start the server.

uv pip install --pre vllm==0.10.1+gptoss \
    --extra-index-url https://wheels.vllm.ai/gpt-oss/ \
    --extra-index-url https://download.pytorch.org/whl/nightly/cu128 \
    --index-strategy unsafe-best-match

vllm serve openai/gpt-oss-120b

Learn more about how to use gpt-oss with vLLM.

PyTorch / Triton

To learn about how to use this model with PyTorch and Triton, check out our reference implementations in the gpt-oss repository.

Ollama

If you are trying to run gpt-oss on consumer hardware, you can use Ollama by running the following commands after installing Ollama.

# gpt-oss-120b
ollama pull gpt-oss:120b
ollama run gpt-oss:120b

Learn more about how to use gpt-oss with Ollama.

LM Studio

If you are using LM Studio you can use the following commands to download.

# gpt-oss-120b
lms get openai/gpt-oss-120b

Check out our awesome list for a broader collection of gpt-oss resources and inference partners.

Download the model

You can download the model weights from the Hugging Face Hub directly from Hugging Face CLI:

# gpt-oss-120b
huggingface-cli download openai/gpt-oss-120b --include "original/*" --local-dir gpt-oss-120b/
pip install gpt-oss
python -m gpt_oss.chat model/

Reasoning levels

You can adjust the reasoning level that suits your task across three levels:

Low: Fast responses for general dialogue.
Medium: Balanced speed and detail.
High: Deep and detailed analysis.

The reasoning level can be set in the system prompts, e.g., "Reasoning: high".

Tool use

The gpt-oss models are excellent for:

Web browsing (using built-in browsing tools)
Function calling with defined schemas
Agentic operations like browser tasks

Fine-tuning

Both gpt-oss models can be fine-tuned for a variety of specialized use cases.

This larger model gpt-oss-120b can be fine-tuned on a single H100 node, whereas the smaller gpt-oss-20b can even be fine-tuned on consumer hardware.

Citation

@misc{openai2025gptoss120bgptoss20bmodel,
      title={gpt-oss-120b & gpt-oss-20b Model Card}, 
      author={OpenAI},
      year={2025},
      eprint={2508.10925},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.10925}, 
}