Instructions to use StealthyML/StealthyLM-Emotive with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use StealthyML/StealthyLM-Emotive 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 StealthyML/StealthyLM-Emotive
# Run inference directly in the terminal:
llama cli -hf StealthyML/StealthyLM-Emotive

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf StealthyML/StealthyLM-Emotive
# Run inference directly in the terminal:
llama cli -hf StealthyML/StealthyLM-Emotive

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 StealthyML/StealthyLM-Emotive
# Run inference directly in the terminal:
./llama-cli -hf StealthyML/StealthyLM-Emotive

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 StealthyML/StealthyLM-Emotive
# Run inference directly in the terminal:
./build/bin/llama-cli -hf StealthyML/StealthyLM-Emotive

Use Docker

docker model run hf.co/StealthyML/StealthyLM-Emotive

LM Studio
Jan
Ollama
How to use StealthyML/StealthyLM-Emotive with Ollama:
```
ollama run hf.co/StealthyML/StealthyLM-Emotive
```

Unsloth Studio

How to use StealthyML/StealthyLM-Emotive 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 StealthyML/StealthyLM-Emotive 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 StealthyML/StealthyLM-Emotive to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for StealthyML/StealthyLM-Emotive to start chatting

How to use StealthyML/StealthyLM-Emotive with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf StealthyML/StealthyLM-Emotive

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": "StealthyML/StealthyLM-Emotive"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use StealthyML/StealthyLM-Emotive with Docker Model Runner:
```
docker model run hf.co/StealthyML/StealthyLM-Emotive
```

Lemonade

How to use StealthyML/StealthyLM-Emotive with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull StealthyML/StealthyLM-Emotive

Run and chat with the model

lemonade run user.StealthyLM-Emotive-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use StealthyML/StealthyLM-Emotive with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf StealthyML/StealthyLM-Emotive

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 StealthyML/StealthyLM-Emotive

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use StealthyML/StealthyLM-Emotive with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf StealthyML/StealthyLM-Emotive

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 "StealthyML/StealthyLM-Emotive" \
  --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"

StealthyLM — Skadoosh Voice Model

Spoken-dialogue engine for Skadoosh. Fine-tuned Qwen2.5-1.5B-Instruct optimized for clause-level streaming TTS, real barge-in, and fully local edge inference.

Why This Model

Skadoosh streams TTS per-clause and supports instant barge-in [[9]]. Standard LLMs break this pipeline with markdown, long responses, and tone-deaf output. StealthyLM fixes all three:

Zero markdown — clean text for Kokoro TTS, no formatting artifacts
Short clauses — matches Skadoosh's clause-level streaming architecture
Emotion-aware — contextual tone matching beyond keyword-driven detect_tone [[9]]
Grounded — says "I'm not sure" instead of hallucinating during tool execution
Edge-ready — Q4_K_M GGUF runs on Raspberry Pi with sub-150ms latency target [[9]]

Quick Start

# Drop into your Skadoosh models directory
mv StealthyLM_Q4KM.gguf models/

# Run Skadoosh with StealthyLM
skadoosh --llm-model StealthyLM_Q4KM.gguf --tts-emotion

Downloads last month: 79

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

StealthyML
/

StealthyLM-Emotive

StealthyLM — Skadoosh Voice Model

Why This Model

Quick Start

Dataset used to train StealthyML/StealthyLM-Emotive