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

Libraries

How to use benhaotang/gpt-oss-coder-20B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="benhaotang/gpt-oss-coder-20B-GGUF",
	filename="gpt-oss-coder-F16.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 benhaotang/gpt-oss-coder-20B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf benhaotang/gpt-oss-coder-20B-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf benhaotang/gpt-oss-coder-20B-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf benhaotang/gpt-oss-coder-20B-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf benhaotang/gpt-oss-coder-20B-GGUF:F16

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 benhaotang/gpt-oss-coder-20B-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf benhaotang/gpt-oss-coder-20B-GGUF:F16

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 benhaotang/gpt-oss-coder-20B-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf benhaotang/gpt-oss-coder-20B-GGUF:F16

Use Docker

docker model run hf.co/benhaotang/gpt-oss-coder-20B-GGUF:F16

LM Studio
Jan

vLLM

How to use benhaotang/gpt-oss-coder-20B-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/benhaotang/gpt-oss-coder-20B-GGUF:F16

Ollama
How to use benhaotang/gpt-oss-coder-20B-GGUF with Ollama:
```
ollama run hf.co/benhaotang/gpt-oss-coder-20B-GGUF:F16
```

Unsloth Studio

How to use benhaotang/gpt-oss-coder-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 benhaotang/gpt-oss-coder-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 benhaotang/gpt-oss-coder-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 benhaotang/gpt-oss-coder-20B-GGUF to start chatting

How to use benhaotang/gpt-oss-coder-20B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf benhaotang/gpt-oss-coder-20B-GGUF:F16

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": "benhaotang/gpt-oss-coder-20B-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use benhaotang/gpt-oss-coder-20B-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 benhaotang/gpt-oss-coder-20B-GGUF:F16

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 benhaotang/gpt-oss-coder-20B-GGUF:F16

Run Hermes

hermes

Docker Model Runner
How to use benhaotang/gpt-oss-coder-20B-GGUF with Docker Model Runner:
```
docker model run hf.co/benhaotang/gpt-oss-coder-20B-GGUF:F16
```

Lemonade

How to use benhaotang/gpt-oss-coder-20B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull benhaotang/gpt-oss-coder-20B-GGUF:F16

Run and chat with the model

lemonade run user.gpt-oss-coder-20B-GGUF-F16

List all available models

lemonade list

Quatized yasserrmd/gpt-oss-coder-20b with llama.cpp commit 54a241f

Thanks for the awesome finetuning work by yasserrmd and OpenAI for the original model.

Multiple ways to use:

run with llama.cpp: ./llama-server -m "gpt-oss-coder-MXFP4_MOE.gguf" -ngl 25 --jinja
use with lmstudio: just pull from benhaotang/gpt-oss-coder-20B-GGUF

Downloads last month: 77

GGUF

Model size

21B params

Architecture

gpt-oss

Hardware compatibility

4-bit

16-bit

Model tree for benhaotang/gpt-oss-coder-20B-GGUF

Base model

openai/gpt-oss-20b

Quantized

unsloth/gpt-oss-20b-unsloth-bnb-4bit

Finetuned

yasserrmd/gpt-oss-coder-20b

Quantized

(4)

this model

benhaotang
/

gpt-oss-coder-20B-GGUF

Model tree for benhaotang/gpt-oss-coder-20B-GGUF

Dataset used to train benhaotang/gpt-oss-coder-20B-GGUF