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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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

Install from WinGet (Windows)

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

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

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

Use Docker

docker model run hf.co/tehkuhnz/gpt-oss-20b

LM Studio
Jan
Ollama
How to use tehkuhnz/gpt-oss-20b with Ollama:
```
ollama run hf.co/tehkuhnz/gpt-oss-20b
```

Unsloth Studio

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

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

Lemonade

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

Pull the model

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

Run and chat with the model

lemonade run user.gpt-oss-20b-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

This model was pulled directly from the ollama model library and then renamed as a GGUF file. This is useful for solutions that require offline inference for Ollama and can not pull directly from the Ollama Library. Specifically, this GGUF will work with Ollama versions (0.11.4) and above. I have found that other GGUF providers for GPT-OSS are still not 100% with Ollama's implementation of the model. This is most likely not observed with lama.cpp, but just wanted an easy way to consume this with the Tanzu AI solutions stack.

Downloads last month: 5

GGUF

Model size

21B params

Architecture

gptoss

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for tehkuhnz/gpt-oss-20b

Base model

openai/gpt-oss-20b

Quantized

(230)

this model