Instructions to use Prince-1/orpheus_3b_0.1_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Prince-1/orpheus_3b_0.1_GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-to-speech", model="Prince-1/orpheus_3b_0.1_GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Prince-1/orpheus_3b_0.1_GGUF", device_map="auto")

llama-cpp-python

How to use Prince-1/orpheus_3b_0.1_GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Prince-1/orpheus_3b_0.1_GGUF",
	filename="unsloth.F16.gguf",
)

llm.create_chat_completion(
	messages = "\"The answer to the universe is 42\""
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Prince-1/orpheus_3b_0.1_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 Prince-1/orpheus_3b_0.1_GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Prince-1/orpheus_3b_0.1_GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Prince-1/orpheus_3b_0.1_GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Prince-1/orpheus_3b_0.1_GGUF: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 Prince-1/orpheus_3b_0.1_GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Prince-1/orpheus_3b_0.1_GGUF: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 Prince-1/orpheus_3b_0.1_GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Prince-1/orpheus_3b_0.1_GGUF:Q4_K_M

Use Docker

docker model run hf.co/Prince-1/orpheus_3b_0.1_GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Prince-1/orpheus_3b_0.1_GGUF with Ollama:
```
ollama run hf.co/Prince-1/orpheus_3b_0.1_GGUF:Q4_K_M
```
Unsloth Desktop

How to use Prince-1/orpheus_3b_0.1_GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Prince-1/orpheus_3b_0.1_GGUF: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": "Prince-1/orpheus_3b_0.1_GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Prince-1/orpheus_3b_0.1_GGUF with Docker Model Runner:
```
docker model run hf.co/Prince-1/orpheus_3b_0.1_GGUF:Q4_K_M
```

Lemonade

How to use Prince-1/orpheus_3b_0.1_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Prince-1/orpheus_3b_0.1_GGUF:Q4_K_M

Run and chat with the model

lemonade run user.orpheus_3b_0.1_GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Prince-1/orpheus_3b_0.1_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 Prince-1/orpheus_3b_0.1_GGUF: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 Prince-1/orpheus_3b_0.1_GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Prince-1/orpheus_3b_0.1_GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Prince-1/orpheus_3b_0.1_GGUF: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 "Prince-1/orpheus_3b_0.1_GGUF: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"

Uploaded model

Finetuned by: Prince-1
License: apache-2.0
Finetuned from model : unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time streaming performances.

Model Details

Model Capabilities

Human-Like Speech: Natural intonation, emotion, and rhythm that is superior to SOTA closed source models
Zero-Shot Voice Cloning: Clone voices without prior fine-tuning
Guided Emotion and Intonation: Control speech and emotion characteristics with simple tags
Low Latency: ~200ms streaming latency for realtime applications, reducible to ~100ms with input streaming

Model Sources

GitHub Repo: https://github.com/canopyai/Orpheus-TTS
Blog Post: https://canopylabs.ai/model-releases
Colab Inference Notebook: notebook link

Quantization

Model is converted into GGUF

Choose quantization_method to be:

not_quantized: Recommended. Fast conversion. Slow inference, big files.
fast_quantized: Recommended. Fast conversion. OK inference, OK file size.
quantized: Recommended. Slow conversion. Fast inference, small files.
f32: Not recommended. Retains 100% accuracy, but super slow and memory hungry.
f16: Fastest conversion + retains 100% accuracy. Slow and memory hungry.
q8_0: Fast conversion. High resource use, but generally acceptable.
q4_k_m: Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K.
q5_k_m: Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K.
q2_k: Uses Q4_K for attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors.
q3_k_l: Uses Q5_K for attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K.
q3_k_m: Uses Q4_K for attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K.
q3_k_s: Uses Q3_K for all tensors.
q4_0: Original quant method, 4-bit.
q4_1: Higher accuracy than q4_0 but not as high as q5_0. However, has quicker inference than q5 models.
q4_k_s: Uses Q4_K for all tensors.
q4_k: Alias for q4_k_m.
q5_k: Alias for q5_k_m.
q5_0: Higher accuracy, higher resource usage and slower inference.
q5_1: Even higher accuracy, resource usage and slower inference.
q5_k_s: Uses Q5_K for all tensors.
q6_k: Uses Q8_K for all tensors.

Usage

The model is utilse using module [llama-cpp-python](https://github.com/abetlen/llama-cpp-python] module) which provide python binding for llama-cpp.

from llama-cpp-python import LLM

Model Misuse

Do not use our models for impersonation without consent, misinformation or deception (including fake news or fraudulent calls), or any illegal or harmful activity. By using this model, you agree to follow all applicable laws and ethical guidelines. We disclaim responsibility for any use.