Instructions to use sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf",
	filename="gpt-oss-20b-reap-0.4-mxfp4-q8_0.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 sandeshrajx/gpt-oss-20b-reap-0.4-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 sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf: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 sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf: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 sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0

Use Docker

docker model run hf.co/sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0

LM Studio
Jan

vLLM

How to use sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-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": "sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0

Ollama
How to use sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf with Ollama:
```
ollama run hf.co/sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0
```

Unsloth Studio

How to use sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-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 sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-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 sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf to start chatting

How to use sandeshrajx/gpt-oss-20b-reap-0.4-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 sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf: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": "sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use sandeshrajx/gpt-oss-20b-reap-0.4-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 sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf: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 sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use sandeshrajx/gpt-oss-20b-reap-0.4-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 sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0

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 "sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0" \
  --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"

Docker Model Runner
How to use sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf with Docker Model Runner:
```
docker model run hf.co/sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0
```

Lemonade

How to use sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4-gguf:Q8_0

Run and chat with the model

lemonade run user.gpt-oss-20b-reap-0.4-mxfp4-gguf-Q8_0

List all available models

lemonade list

gpt-oss-20b-reap-0.4-mxfp4-gguf

This repository contains a GGUF quantized version of the sandeshrajx/gpt-oss-20b-reap-0.4-mxfp4 model.

Model Description

This model is a GGUF quantized version of the MXFP4 quantized openai/gpt-oss-20b model.

Original Model: openai/gpt-oss-20b
Pruning Method: reap with a compression ratio of 0.4
First Quantization Method: MXFP4 weight-only quantization
Second Quantization Method: GGUF (Q8_0) using llama.cpp
Dataset used for pruning/quantization (if applicable): theblackcat102/evol-codealpaca-v1

The original MXFP4 quantization specifically targeted the "expert" layers of the model, skipping self-attention and router layers, as is standard practice for Mixture-of-Experts (MoE) models to optimize performance and reduce size. This GGUF quantization further reduces the model size for efficient inference with llama.cpp.

Usage

You can use this model with llama.cpp or compatible GGUF loaders.

Quantization Details

The model was first pruned with a 0.4 compression ratio using reap, then quantized to MXFP4. Subsequently, it was converted to GGUF (Q8_0) format using the llama.cpp conversion script.

Pruning Commands Used:

python ./reap/src/reap/prune.py \
    --model-name "openai/gpt-oss-20b" \
    --run_observer_only true \
    --samples_per_category 32

python ./reap/src/reap/prune.py \
    --model-name "openai/gpt-oss-20b" \
    --compression-ratio 0.4 \
    --prune-method reap

MXFP4 Quantization Command Used:

python Model-Optimizer/examples/gpt-oss/convert_oai_mxfp4_weight_only.py \
    --model_path /workspace/artifacts/gpt-oss-20b/evol-codealpaca-v1/pruned_models/reap-seed_42-0.4-mxfp4 \
    --output_path /workspace/artifacts/gpt-oss-20b/evol-codealpaca-v1/pruned_models/reap-seed_42-0.4-mxfp4-quantized

GGUF Quantization Command Used:

python llama.cpp/convert_hf_to_gguf.py \
    --outtype q8_0 \
    --outfile /path/to/output/gpt-oss-20b-reap-0.4-mxfp4-q8_0.gguf \
    /path/to/downloaded/mxfp4_model

License

(Please specify the license of the original model and any modifications)

Downloads last month: 17

GGUF

Model size

14B params

Architecture

gpt-oss

Hardware compatibility

8-bit