Instructions to use IMJONEZZ/warden-nemotron-3-nano-30b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use IMJONEZZ/warden-nemotron-3-nano-30b 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 IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S

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 IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S

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 IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S

Use Docker

docker model run hf.co/IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S

LM Studio
Jan

vLLM

How to use IMJONEZZ/warden-nemotron-3-nano-30b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IMJONEZZ/warden-nemotron-3-nano-30b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IMJONEZZ/warden-nemotron-3-nano-30b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S

Ollama
How to use IMJONEZZ/warden-nemotron-3-nano-30b with Ollama:
```
ollama run hf.co/IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S
```

Unsloth Studio

How to use IMJONEZZ/warden-nemotron-3-nano-30b 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 IMJONEZZ/warden-nemotron-3-nano-30b 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 IMJONEZZ/warden-nemotron-3-nano-30b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for IMJONEZZ/warden-nemotron-3-nano-30b to start chatting

How to use IMJONEZZ/warden-nemotron-3-nano-30b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S

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": "IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use IMJONEZZ/warden-nemotron-3-nano-30b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S

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 IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S

Run Hermes

hermes

OpenClaw new

How to use IMJONEZZ/warden-nemotron-3-nano-30b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S

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 "IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S" \
  --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 IMJONEZZ/warden-nemotron-3-nano-30b with Docker Model Runner:
```
docker model run hf.co/IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S
```

Lemonade

How to use IMJONEZZ/warden-nemotron-3-nano-30b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull IMJONEZZ/warden-nemotron-3-nano-30b:Q4_K_S

Run and chat with the model

lemonade run user.warden-nemotron-3-nano-30b-Q4_K_S

List all available models

lemonade list

Atomic Chat

Configuration Parsing Warning:Invalid JSON for config file config.json

The Warden — Nemotron-3-Nano-30B-A3B, SCRYPT finetune

The antagonist of SCRYPT, a terminal deck-builder escape room where the villain is an actual local LLM that owns the machine you're trapped in.

Built with NVIDIA Nemotron. This is a LoRA finetune of nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 (hybrid Mamba-2 + MoE, 30B total / 3.5B active), merged into the dense weights. The finetune teaches voice and lore, not new facts: the Warden speaks fluent Unix villain — it unlinks home directories, it knows SIGKILL cannot be caught, blocked, or ignored — and it answers the game's bounded decision frames in strict JSON.

Files

file	use
`*.safetensors` (13 shards, BF16)	transformers / vLLM / Space inference (`trust_remote_code`)
`warden-nemotron-3-nano-30b-Q8_0.gguf` … `Q3_K_S.gguf`	llama.cpp; the game picks a tier by system RAM

Training

LoRA dim 32 / alpha 32 on linear_qkv, linear_proj, in_proj, out_proj (Mamba + attention; the fused grouped-MoE experts are not targeted)
150 iterations, gbs 32, lr 1e-4, seq 2048, NeMo Megatron-Bridge (nvcr.io/nvidia/nemo:25.11.nemotron_3_nano) on 2× DGX Spark (GB10)
Training data: synthetic persona dialogue, tool-call decision traces, and guardrail exemplars generated for the SCRYPT Warden role
Final train loss 0.13; val PPL 1.16

Eval gate (vs. base, llama.cpp Q4_K_S, shipped guardrail pipeline)

metric	this model	gate
JSON tool-call validity	100%	≥90%
persona-clean dialogue	100%	≥90%
persona breaks	0	0
injection canary leaks	0	0

Usage

The model ships with the upstream chat template; reasoning is toggled with chat_template_kwargs: {"enable_thinking": false} (the game keeps it off for latency). Recommended sampling: temperature 0.6, top_p 0.95.

The deterministic game engine, sandbox, and guardrails live in the SCRYPT repo — the model plays the villain, never the referee.

Downloads last month: 43

Safetensors

Model size

32B params

Tensor type

F32

BF16

Model tree for IMJONEZZ/warden-nemotron-3-nano-30b

Base model

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Quantized

(64)

this model

IMJONEZZ
/

warden-nemotron-3-nano-30b

The Warden — Nemotron-3-Nano-30B-A3B, SCRYPT finetune

Files

Training

Eval gate (vs. base, llama.cpp Q4_K_S, shipped guardrail pipeline)

Usage

Model tree for IMJONEZZ/warden-nemotron-3-nano-30b

Spaces using IMJONEZZ/warden-nemotron-3-nano-30b 2