Instructions to use SamPurkis/gpt-oss-puzzle-88B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SamPurkis/gpt-oss-puzzle-88B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SamPurkis/gpt-oss-puzzle-88B-GGUF",
	filename="gpt-oss-puzzle-88B.MXFP4_MOE.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SamPurkis/gpt-oss-puzzle-88B-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 SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
llama cli -hf SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
llama cli -hf SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE

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 SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
./llama-cli -hf SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE

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 SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE

Use Docker

docker model run hf.co/SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE

LM Studio
Jan
Ollama
How to use SamPurkis/gpt-oss-puzzle-88B-GGUF with Ollama:
```
ollama run hf.co/SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE
```

Unsloth Studio

How to use SamPurkis/gpt-oss-puzzle-88B-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 SamPurkis/gpt-oss-puzzle-88B-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 SamPurkis/gpt-oss-puzzle-88B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SamPurkis/gpt-oss-puzzle-88B-GGUF to start chatting

How to use SamPurkis/gpt-oss-puzzle-88B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE

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": "SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SamPurkis/gpt-oss-puzzle-88B-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 SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE

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 SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use SamPurkis/gpt-oss-puzzle-88B-GGUF with Docker Model Runner:
```
docker model run hf.co/SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE
```

Lemonade

How to use SamPurkis/gpt-oss-puzzle-88B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SamPurkis/gpt-oss-puzzle-88B-GGUF:MXFP4_MOE

Run and chat with the model

lemonade run user.gpt-oss-puzzle-88B-GGUF-MXFP4_MOE

List all available models

lemonade list

gpt-oss-puzzle-88B-GGUF

EXPERIMENTAL - REQUIRES CUSTOM BRANCH

These GGUF files will NOT work with mainline llama.cpp. You must use the branch linked below.

GGUF quantisation of nvidia/gpt-oss-puzzle-88B, an 88B parameter MoE model derived from gpt-oss-120B using NVIDIA's Puzzle NAS framework.

Required Branch

This model requires a custom llama.cpp branch with gpt-oss-puzzle architecture support:

https://github.com/smpurkis/llama.cpp/tree/gpt-oss-puzzle-support

Tracking issue: ggml-org/llama.cpp#21028 PR: ggml-org/llama.cpp#21032

This will not work on mainline llama.cpp until the architecture is merged upstream.

How to Use

# Clone the required branch
git clone --branch gpt-oss-puzzle-support https://github.com/smpurkis/llama.cpp.git
cd llama.cpp

# Build (example with Vulkan)
cmake -B build -DGGML_VULKAN=1
cmake --build build --config Release -j$(nproc)

# Run
./build/bin/llama-cli -m gpt-oss-puzzle-88B.MXFP4_MOE.gguf -ngl 99 -fa 1 -p "Hello"

Available Quantisations

File	Quant	Size	Description
`gpt-oss-puzzle-88B.f16.gguf`	F16	47.0 GiB	Full precision (for requantisation)
`gpt-oss-puzzle-88B.MXFP4_MOE.gguf`	MXFP4_MOE	44.8 GiB	Native MXFP4 expert weights (matches original model precision)

Architecture Differences from gpt-oss-120B

The puzzle model differs from the standard gpt-oss architecture in ways that require dedicated support:

Property	gpt-oss-120B	gpt-oss-puzzle-88B
Expert count	128 per layer (uniform)	128 or 64 per layer (heterogeneous)
Attention pattern	Interleaved global/SWA (single window)	Global + multiple SWA window sizes (128, 8192)
Total parameters	~117B	~88B

Credits

Original model: NVIDIA
llama.cpp architecture support: smpurkis/llama.cpp@gpt-oss-puzzle-support

Downloads last month: 117

GGUF

Model size

88B params

Architecture

gpt-oss-puzzle

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

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

Model tree for SamPurkis/gpt-oss-puzzle-88B-GGUF

Base model

nvidia/gpt-oss-puzzle-88B

Quantized

(1)

this model

Paper for SamPurkis/gpt-oss-puzzle-88B-GGUF

Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

Paper • 2411.19146 • Published Nov 28, 2024 • 20