Instructions to use eugenehp/miotts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eugenehp/miotts with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="eugenehp/miotts",
	filename="MioTTS-0.6B-Q4_K_M.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 eugenehp/miotts 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 eugenehp/miotts:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf eugenehp/miotts:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/eugenehp/miotts:Q4_K_M

LM Studio
Jan
Ollama
How to use eugenehp/miotts with Ollama:
```
ollama run hf.co/eugenehp/miotts:Q4_K_M
```

Unsloth Studio

How to use eugenehp/miotts 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 eugenehp/miotts 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 eugenehp/miotts to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for eugenehp/miotts to start chatting

Atomic Chat new
Docker Model Runner
How to use eugenehp/miotts with Docker Model Runner:
```
docker model run hf.co/eugenehp/miotts:Q4_K_M
```

Lemonade

How to use eugenehp/miotts with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull eugenehp/miotts:Q4_K_M

Run and chat with the model

lemonade run user.miotts-Q4_K_M

List all available models

lemonade list

MioTTS-0.6B (RLX staging)

MioTTS-0.6B speech LM + presets/samples for RLX.

Field	Value
Hub id	`eugenehp/miotts`
Kind	Staging redistrib of an upstream checkpoint for RLX runners.
RLX crate	`rlx-miotts`
Upstream	https://huggingface.co/Aratako/MioTTS-0.6B

Quick start

hf download eugenehp/miotts --local-dir .
cargo run -p rlx-miotts --release -- --model-dir . --codec-dir ../miocodec

File highlights

model.safetensors (1.1 GiB)
MioTTS-0.6B-Q4_K_M.gguf (388.6 MiB)
tokenizer.json (13.2 MiB)
vocab.json (2.6 MiB)
tokenizer_config.json (2.2 MiB)
merges.txt (1.6 MiB)
added_tokens.json (302.3 KiB)
config.json (1.3 KiB)
special_tokens_map.json (613 B)
chat_template.jinja (205 B)
generation_config.json (160 B)

Run with RLX

Clone rlx-models, place this repo under weights/tts/miotts (or pass the path explicitly), then:

cargo run -p rlx-miotts --release -- --model-dir . --codec-dir ../miocodec

License

Apache License 2.0 — see LICENSE. Inherit upstream terms when redistributing.

Original weights and authorship: https://huggingface.co/Aratako/MioTTS-0.6B

Redistrib note

This Hub repo exists so RLX recipes have a stable fetch target. When you only need the upstream checkpoint, prefer the Upstream link above.

Downloads last month: 61

Safetensors

Model size

0.6B params

Tensor type

BF16