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

Libraries

How to use unsloth/gpt-oss-20b-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="unsloth/gpt-oss-20b-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/gpt-oss-20b-GGUF")
model = AutoModelForCausalLM.from_pretrained("unsloth/gpt-oss-20b-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/gpt-oss-20b-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 unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama cli -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

Llama new
LM Studio
Jan

vLLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/gpt-oss-20b-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "unsloth/gpt-oss-20b-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gpt-oss-20b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "unsloth/gpt-oss-20b-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gpt-oss-20b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/gpt-oss-20b-GGUF with Ollama:
```
ollama run hf.co/unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
```
Unsloth Desktop

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

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": "unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use unsloth/gpt-oss-20b-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.gpt-oss-20b-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use unsloth/gpt-oss-20b-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 unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

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 unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use unsloth/gpt-oss-20b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL

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 "unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL" \
  --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"

Getting tensor 'blk.0.ffn_down_exps.weight' has invalid ggml type 39 (NONE) error when trying to load the model in llama.cpp

by KernelDebugger - opened Aug 5, 2025

Discussion

KernelDebugger

Aug 5, 2025

Hello. Trying to load the model in llama.cpp (cli and server) and getting this error:

srv load_model: loading model '../../../gpt-oss-20b-F16.gguf'
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 4070 Ti SUPER) - 15429 MiB free
gguf_init_from_file_impl: tensor 'blk.0.ffn_down_exps.weight' has invalid ggml type 39 (NONE)
gguf_init_from_file_impl: failed to read tensor info
llama_model_load: error loading model: llama_model_loader: failed to load model from ../../../gpt-oss-20b-F16.gguf
llama_model_load_from_file_impl: failed to load model
common_init_from_params: failed to load model '../../../gpt-oss-20b-F16.gguf'
srv load_model: failed to load model, '../../../gpt-oss-20b-F16.gguf'
srv operator(): operator(): cleaning up before exit...

JamesMowery

Aug 5, 2025

•

edited Aug 5, 2025

Also seeing this. Although in the other thread it was mentioned that a new version is coming with fixes regarding chat template. Hopefully that fix is also fixing this? But if not, then this needs attention as well!

KernelDebugger

Aug 5, 2025

•

edited Aug 5, 2025

I think I’ve downloaded the fixed version. Exactly under the link "This is the new MXFP4_MOE quant renamed to F16 with our chat template fixes! Use GGUFs here."
And it shows this error.

JamesMowery

Aug 5, 2025

•

edited Aug 5, 2025

Referring to this comment: https://huggingface.co/unsloth/gpt-oss-20b-GGUF/discussions/2#68927da38491c63d06a29dd6

This was posted 20 minutes ago, and the models were uploaded 1 hour ago and the readme was updated like 40 or so minutes ago, so I'm assuming another upload is coming. But I'm not 100% sure.

But, as mentioned, I'm also seeing this error. So I'm just waiting for fixes.