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

Libraries

How to use unsloth/gpt-oss-20b-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="unsloth/gpt-oss-20b-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/gpt-oss-20b-GGUF")
model = AutoModelForCausalLM.from_pretrained("unsloth/gpt-oss-20b-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/gpt-oss-20b-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 unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

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 unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

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 unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/gpt-oss-20b-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": "unsloth/gpt-oss-20b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/gpt-oss-20b-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "unsloth/gpt-oss-20b-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gpt-oss-20b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "unsloth/gpt-oss-20b-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gpt-oss-20b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/gpt-oss-20b-GGUF with Ollama:
```
ollama run hf.co/unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/gpt-oss-20b-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 unsloth/gpt-oss-20b-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 unsloth/gpt-oss-20b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/gpt-oss-20b-GGUF to start chatting

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

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": "unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/gpt-oss-20b-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 unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

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 unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use unsloth/gpt-oss-20b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

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 "unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL" \
  --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 unsloth/gpt-oss-20b-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.gpt-oss-20b-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Are the F16 weights upcasted MXFP4? -- Why no `gpt-oss-20b-MXFP4.gguf`?

#34

by rtzurtz - opened Oct 19, 2025

Discussion

rtzurtz

Oct 19, 2025

Follow up question to https://huggingface.co/unsloth/gpt-oss-20b-GGUF/discussions/14 and https://huggingface.co/unsloth/gpt-oss-20b-GGUF/discussions/7:

Are the F16 weights maybe just upcasted MXFP4 ones, or why is bartowski recommending to use gpt-oss-20b-MXFP4.gguf (12.1 GB):

Use this one:
gpt-oss-20b-MXFP4.gguf
The reason is, the FFN (feed forward networks) of gpt-oss do not behave nicely when quantized to anything other than MXFP4, so they are kept at that level for everything.

, everyone in https://github.com/ggml-org/llama.cpp/discussions/15396 is also testing only the gpt-oss-20b-MXFP4.gguf and just another example, lmstudio-community also only has the gpt-oss-20b-MXFP4.gguf?

qikchen

Oct 20, 2025

Yes, I think only using MXFP4.gguf is the way to go with gpt oss. Unsloth GGUFs aren't applicable AFAIK in this model.
I think they have anyway made all their GGUFs for a completion's sake. And perhaps the quantization under Q4 also has value for people without enough vram. But if you can use Q4, it only makes sense to use the standard *-MXFP4.ggufs.

danielhanchen

Unsloth AI org Nov 1, 2025

The other MXFP4 GGUFs are actually quantized down to 8bit so it's not true 100% full precision. The f16 versions retain the model's full original precision. The difference shouldn't be much but regardless, there is a difference between them.

Our MXFP4 versions (like the others) are actually the Q8 ones. While the true full precision is f16.

rtzurtz

Nov 7, 2025

@danielhanchen Thanks for the info. Maybe clarify this in the model card as well (not everyone is going to read the comments). (So this *-MXFP4.gguf, which many quant to, is just the latest fake hype, because quanting to MXFP4 is not the same as QATing to MXFP4 (a bit nice wording game by me indeed btw.))

Before creating my question, I did some testing, and maybe the F16 was a bit better, but for the short testing, I decided the result was inconclusive. But now, that it's clarified, I still may revert back to the full F16 weights.

Maybe this is partly the reason for my confusion:

The F32 quant is MXFP4 upcasted to BF16 for every single layer and is unquantized.

PS: Can't find the F32 quant (just a hint, not that I need one).

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