Instructions to use Joseph717171/Gpt-OSS-20B-MXFP4-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 Joseph717171/Gpt-OSS-20B-MXFP4-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 Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4
# Run inference directly in the terminal:
llama cli -hf Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4
# Run inference directly in the terminal:
llama cli -hf Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4

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 Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4
# Run inference directly in the terminal:
./llama-cli -hf Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4

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 Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4

Use Docker

docker model run hf.co/Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4

LM Studio
Jan
Ollama
How to use Joseph717171/Gpt-OSS-20B-MXFP4-GGUF with Ollama:
```
ollama run hf.co/Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4
```
Unsloth Desktop

How to use Joseph717171/Gpt-OSS-20B-MXFP4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Joseph717171/Gpt-OSS-20B-MXFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4
```

Lemonade

How to use Joseph717171/Gpt-OSS-20B-MXFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4

Run and chat with the model

lemonade run user.Gpt-OSS-20B-MXFP4-GGUF-MXFP4

List all available models

lemonade list

Hermes Agent

How to use Joseph717171/Gpt-OSS-20B-MXFP4-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 Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4

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 Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Joseph717171/Gpt-OSS-20B-MXFP4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4

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 "Joseph717171/Gpt-OSS-20B-MXFP4-GGUF:MXFP4" \
  --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"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Gpt-OSS-20B-MXFP4-GGUF

GGUF MXFP4_MOE quant of openai/gpt-OSS-20b. This GGUF model was quantized from the dequantized/Upcasted F32 of the model (not including the MoE layers - as per ggeranov's assertion: "we don't mess with the bits and their placement. We just trust that OpenAI did a good job" and convert from HuggingFace to GGUF). This was done to help preserve and improve the model's accuracy and precision post quantization.

Note: After further experimentation, it turns out it is best to keep the MXFP4 MoE layers in their given state and not fully-dequantize/Upcast to F32. Because, for the aforementioned reason from ggeranov, this leads to a regression in performance. The only reason this is a reality for us, is because llama.cpp just converts from HuggingFace to GGUF for the MOE_Layers. If this wasn't the case, my method for dequantizing/upcasting the model weights to F32 and quantizing would remain the best method for quantizing. And, I would like to add that when llama.cpp finally supports imatrix calibration/training for the MXFP4 MOE layers, we should be able to fully-dequantize/upcast the model weights, calibrate/train an imatrix for it and then quantize using the imatrix to improve the quants accuracy and model preservation. But, unfortunately, we are still waiting for that PR to be made manifest. So, in the meantime, here's the best next option.

filesize: (~12.11 GB)

Downloads last month: 87

GGUF

Model size

21B params

Architecture

gpt-oss

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support