Instructions to use mesh-ops/gpt-oss-20b-base-MXFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mesh-ops/gpt-oss-20b-base-MXFP4-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mesh-ops/gpt-oss-20b-base-MXFP4-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mesh-ops/gpt-oss-20b-base-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 mesh-ops/gpt-oss-20b-base-MXFP4-GGUF:MXFP4
# Run inference directly in the terminal:
llama cli -hf mesh-ops/gpt-oss-20b-base-MXFP4-GGUF:MXFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mesh-ops/gpt-oss-20b-base-MXFP4-GGUF:MXFP4
# Run inference directly in the terminal:
llama cli -hf mesh-ops/gpt-oss-20b-base-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 mesh-ops/gpt-oss-20b-base-MXFP4-GGUF:MXFP4
# Run inference directly in the terminal:
./llama-cli -hf mesh-ops/gpt-oss-20b-base-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 mesh-ops/gpt-oss-20b-base-MXFP4-GGUF:MXFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mesh-ops/gpt-oss-20b-base-MXFP4-GGUF:MXFP4

Use Docker

docker model run hf.co/mesh-ops/gpt-oss-20b-base-MXFP4-GGUF:MXFP4

LM Studio
Jan
Ollama
How to use mesh-ops/gpt-oss-20b-base-MXFP4-GGUF with Ollama:
```
ollama run hf.co/mesh-ops/gpt-oss-20b-base-MXFP4-GGUF:MXFP4
```
Unsloth Desktop

How to use mesh-ops/gpt-oss-20b-base-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 mesh-ops/gpt-oss-20b-base-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": "mesh-ops/gpt-oss-20b-base-MXFP4-GGUF:MXFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mesh-ops/gpt-oss-20b-base-MXFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/mesh-ops/gpt-oss-20b-base-MXFP4-GGUF:MXFP4
```

Lemonade

How to use mesh-ops/gpt-oss-20b-base-MXFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mesh-ops/gpt-oss-20b-base-MXFP4-GGUF:MXFP4

Run and chat with the model

lemonade run user.gpt-oss-20b-base-MXFP4-GGUF-MXFP4

List all available models

lemonade list

Hermes Agent

How to use mesh-ops/gpt-oss-20b-base-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 mesh-ops/gpt-oss-20b-base-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 mesh-ops/gpt-oss-20b-base-MXFP4-GGUF:MXFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mesh-ops/gpt-oss-20b-base-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 mesh-ops/gpt-oss-20b-base-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 "mesh-ops/gpt-oss-20b-base-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"

Quantized to MXFP4 using llama.cpp b6150

I also gguf-my-repo'd a q6_K on my personal account but it's actually not any better and it's too big. looks like llama.cpp quantization is bad quality for these models except for mxfp4

Downloads last month: 30

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

Model tree for mesh-ops/gpt-oss-20b-base-MXFP4-GGUF

Base model

jxm/gpt-oss-20b-base

Quantized

(5)

this model

mesh-ops
/

gpt-oss-20b-base-MXFP4-GGUF

Model tree for mesh-ops/gpt-oss-20b-base-MXFP4-GGUF

Dataset used to train mesh-ops/gpt-oss-20b-base-MXFP4-GGUF