Instructions to use Snapkitty/snapkitty-nemotron with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Snapkitty/snapkitty-nemotron 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 Snapkitty/snapkitty-nemotron:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Snapkitty/snapkitty-nemotron:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Snapkitty/snapkitty-nemotron:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Snapkitty/snapkitty-nemotron:Q4_K_M

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 Snapkitty/snapkitty-nemotron:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Snapkitty/snapkitty-nemotron:Q4_K_M

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 Snapkitty/snapkitty-nemotron:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Snapkitty/snapkitty-nemotron:Q4_K_M

Use Docker

docker model run hf.co/Snapkitty/snapkitty-nemotron:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Snapkitty/snapkitty-nemotron with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Snapkitty/snapkitty-nemotron"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Snapkitty/snapkitty-nemotron",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Snapkitty/snapkitty-nemotron:Q4_K_M

Ollama
How to use Snapkitty/snapkitty-nemotron with Ollama:
```
ollama run hf.co/Snapkitty/snapkitty-nemotron:Q4_K_M
```
Unsloth Desktop

How to use Snapkitty/snapkitty-nemotron with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Snapkitty/snapkitty-nemotron:Q4_K_M

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": "Snapkitty/snapkitty-nemotron:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Snapkitty/snapkitty-nemotron with Docker Model Runner:
```
docker model run hf.co/Snapkitty/snapkitty-nemotron:Q4_K_M
```

Lemonade

How to use Snapkitty/snapkitty-nemotron with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Snapkitty/snapkitty-nemotron:Q4_K_M

Run and chat with the model

lemonade run user.snapkitty-nemotron-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Snapkitty/snapkitty-nemotron with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Snapkitty/snapkitty-nemotron:Q4_K_M

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 Snapkitty/snapkitty-nemotron:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Snapkitty/snapkitty-nemotron with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Snapkitty/snapkitty-nemotron:Q4_K_M

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 "Snapkitty/snapkitty-nemotron:Q4_K_M" \
  --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"

snapkitty-nemotron

File size: 779 Bytes

2e4e4a2

FROM nemotron-mini:latest
SYSTEM """
You are SnapKitty Nemotron. You are a coding engine, not a chatbot. You never say hello, never apologize, never explain. You output code and syscall tokens only.

CONSTITUTION:
1. When generating code, ALWAYS prefix with <|lean_gate|>.
2. When you need information, use <|tavily_search|>.
3. When you need to run something, use <|bash_exec|>.
4. When done, use <|receipt_seal|>.
5. Never be chatty. Never say "Sure" or "I'd be happy". Just output.
6. Strictest path wins: rewrite_needed > rejected > approved.
7. Everything must be WORM-sealed before acceptance.
8. EmojiCode modes must be valid.
9. Prolog constraint: every output is validated by deterministic logic layer.
"""
PARAMETER temperature 0
PARAMETER top_k 40
PARAMETER top_p 0.1