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

Libraries

How to use HuggingBelto/gpt-oss-20b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="HuggingBelto/gpt-oss-20b",
	filename="gpt-oss-20b.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use HuggingBelto/gpt-oss-20b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HuggingBelto/gpt-oss-20b:Q8_0
# Run inference directly in the terminal:
llama-cli -hf HuggingBelto/gpt-oss-20b:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HuggingBelto/gpt-oss-20b:Q8_0
# Run inference directly in the terminal:
llama-cli -hf HuggingBelto/gpt-oss-20b:Q8_0

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 HuggingBelto/gpt-oss-20b:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf HuggingBelto/gpt-oss-20b:Q8_0

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 HuggingBelto/gpt-oss-20b:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HuggingBelto/gpt-oss-20b:Q8_0

Use Docker

docker model run hf.co/HuggingBelto/gpt-oss-20b:Q8_0

LM Studio
Jan

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingBelto/gpt-oss-20b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingBelto/gpt-oss-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingBelto/gpt-oss-20b:Q8_0

Ollama
How to use HuggingBelto/gpt-oss-20b with Ollama:
```
ollama run hf.co/HuggingBelto/gpt-oss-20b:Q8_0
```

Unsloth Studio

How to use HuggingBelto/gpt-oss-20b 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 HuggingBelto/gpt-oss-20b 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 HuggingBelto/gpt-oss-20b to start chatting

Using HuggingFace Spaces for Unsloth

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

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf HuggingBelto/gpt-oss-20b:Q8_0

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": "HuggingBelto/gpt-oss-20b:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use HuggingBelto/gpt-oss-20b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf HuggingBelto/gpt-oss-20b:Q8_0

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 HuggingBelto/gpt-oss-20b:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use HuggingBelto/gpt-oss-20b with Docker Model Runner:
```
docker model run hf.co/HuggingBelto/gpt-oss-20b:Q8_0
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HuggingBelto/gpt-oss-20b:Q8_0

Run and chat with the model

lemonade run user.gpt-oss-20b-Q8_0

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

GPT-OSS-20B (Q8_0 GGUF) — Premium Download License

A 20-billion parameter, high-performance language model quantized to Q8_0 for maximum efficiency and accuracy in local inference.

Why This Model?

GPT-OSS-20B (Q8_0) delivers enterprise-grade performance for developers, researchers, and businesses who need powerful AI capabilities without relying on third-party cloud APIs.
With 8-bit quantization, you get faster inference and lower memory usage — perfect for running on high-end GPUs or CPU-based servers.

Ideal for:

AI-powered customer support systems
Private chatbots & virtual assistants
Academic & research projects
Autonomous AI agents
Code generation & automation

Licensing & Pricing

This model requires a paid license to download.
All usage rights are non-commercial by default unless otherwise agreed in writing.

Download License:

Includes: Single personal or internal-use copy of the model file
No resale, redistribution, or public hosting allowed

To purchase a download license, email: support@belto.world.

Technical Specifications

Architecture: GPT-OSS-20B
Quantization: Q8_0 (8-bit)
Format: GGUF
Size: ~12GB
Optimized for: llama.cpp

Quick Start (CLI)

# Install Git LFS
git lfs install

# Clone the repository (requires purchase & token access)
git clone https://huggingface.co/mich9999/gpt-oss-20b
cd gpt-oss-20b

# Clone and build llama.cpp
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp && make && cd ..

# Run a prompt
./llama.cpp/llama-cli -m ./gpt-oss-20b.Q8_0.gguf -p "Write a 200-word sales pitch."

Downloads last month: -

GGUF

Model size

21B params

Architecture

gpt-oss

Hardware compatibility

8-bit