Instructions to use lex-au/Orpheus-3b-Kaya-Q6_K.gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lex-au/Orpheus-3b-Kaya-Q6_K.gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lex-au/Orpheus-3b-Kaya-Q6_K.gguf",
	filename="Orpheus-3b-Kaya-Q6_K.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 lex-au/Orpheus-3b-Kaya-Q6_K.gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K
# Run inference directly in the terminal:
llama-cli -hf lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K
# Run inference directly in the terminal:
llama-cli -hf lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K

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 lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K

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 lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K

Use Docker

docker model run hf.co/lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K

LM Studio
Jan
Ollama
How to use lex-au/Orpheus-3b-Kaya-Q6_K.gguf with Ollama:
```
ollama run hf.co/lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K
```

Unsloth Studio

How to use lex-au/Orpheus-3b-Kaya-Q6_K.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 lex-au/Orpheus-3b-Kaya-Q6_K.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 lex-au/Orpheus-3b-Kaya-Q6_K.gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lex-au/Orpheus-3b-Kaya-Q6_K.gguf to start chatting

How to use lex-au/Orpheus-3b-Kaya-Q6_K.gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K

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": "lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lex-au/Orpheus-3b-Kaya-Q6_K.gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K

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 lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use lex-au/Orpheus-3b-Kaya-Q6_K.gguf with Docker Model Runner:
```
docker model run hf.co/lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K
```

Lemonade

How to use lex-au/Orpheus-3b-Kaya-Q6_K.gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lex-au/Orpheus-3b-Kaya-Q6_K.gguf:Q6_K

Run and chat with the model

lemonade run user.Orpheus-3b-Kaya-Q6_K.gguf-Q6_K

List all available models

lemonade list

lex-au commited on Apr 19, 2025

Commit

46017d4

verified ·

1 Parent(s): 11c30c5

Update README.md

Browse files

Files changed (1) hide show

README.md +72 -12

README.md CHANGED Viewed

@@ -1,22 +1,82 @@
 ---
-base_model: unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit
 tags:
-- text-generation-inference
-- transformers
-- unsloth
-- llama
 - gguf
 license: apache-2.0
-language:
-- en
 ---
-# Uploaded  model
-- **Developed by:** lex-au
-- **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](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 ---
+language: en
 tags:
+- text-to-speech
+- tts
+- audio
+- speech-synthesis
+- orpheus
 - gguf
+- unsloth
 license: apache-2.0
+datasets:
+- lex-au/Orpheus-3b-Kaya
+---
+# Orpheus-3b-Kaya-Q6_K
+This is a **fine-tuned version** of the pretrained model [canopylabs/orpheus-3b-0.1-pretrained](https://huggingface.co/canopylabs/orpheus-3b-0.1-pretrained), trained on a custom voice dataset and quantised to GGUF Q6_K format for fast, efficient inference.
 ---
+## 🔧 Model Details
+- **Model Type**: Text-to-Speech (TTS)
+- **Architecture**: Token-to-audio language model
+- **Parameters**: ~3 billion
+- **Quantisation**: 8-bit GGUF (Q6_K)
+- **Sampling Rate**: 24kHz mono
+- **Training Epochs**: 1
+- **Training Dataset**: [lex-au/Orpheus-3b-Kaya](https://huggingface.co/datasets/lex-au/Orpheus-3b-Kaya)
+- **Languages**: English
+---
+## 🚀 Quick Usage
+This model is designed for use with [Orpheus-FastAPI](https://github.com/Lex-au/Orpheus-FastAPI), an OpenAI-compatible inference server for text-to-speech generation.
+### Compatible Inference Servers
+You can load this model into:
+- [GPUStack](https://github.com/gpustack/gpustack)
+- [LM Studio](https://lmstudio.ai/)
+- [llama.cpp](https://github.com/ggerganov/llama.cpp)
+- Any other GGUF-compatible OpenAI-style server
+## 📜 License
+Apache License 2.0 — free for research and commercial use.
+---
+## 🙌 Credits
+- Original model by: [Canopy Labs](https://huggingface.co/canopylabs/orpheus-3b-0.1-pt)
+- Fine-tuned, quantised, and API-wrapped by: [Lex-au](https://huggingface.co/lex-au) via [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+---
+## 📚 Citation
+```
+@misc{orpheus-tts-2025,
+  author = {Canopy Labs},
+  title = {Orpheus-3b-0.1-pt: Pretrained Text-to-Speech Model},
+  year = {2025},
+  publisher = {HuggingFace},
+  howpublished = {\url{https://huggingface.co/canopylabs/orpheus-3b-0.1-pt}}
+}
+@misc{orpheus-kaya-2025,
+  author = {Lex-au},
+  title = {Orpheus-3b-Kaya-Q6_K: Fine-Tuned TTS Model (Quantised)},
+  note = {Fine-tuned from canopylabs/orpheus-3b-0.1-pt},
+  year = {2025},
+  publisher = {HuggingFace},
+  howpublished = {\url{https://huggingface.co/lex-au/Orpheus-3b-Kaya-Q6_K}}
+}
+```