TTS models ๐ฃ๏ธ
Collection
13 items โข Updated โข 11
How to use ggml-org/MiniMax-Music3-GGUF with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf ggml-org/MiniMax-Music3-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf ggml-org/MiniMax-Music3-GGUF:BF16
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ggml-org/MiniMax-Music3-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf ggml-org/MiniMax-Music3-GGUF:BF16
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf ggml-org/MiniMax-Music3-GGUF:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf ggml-org/MiniMax-Music3-GGUF:BF16
docker model run hf.co/ggml-org/MiniMax-Music3-GGUF:BF16
How to use ggml-org/MiniMax-Music3-GGUF with Ollama:
ollama run hf.co/ggml-org/MiniMax-Music3-GGUF:BF16
How to use ggml-org/MiniMax-Music3-GGUF with Docker Model Runner:
docker model run hf.co/ggml-org/MiniMax-Music3-GGUF:BF16
How to use ggml-org/MiniMax-Music3-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ggml-org/MiniMax-Music3-GGUF:BF16
lemonade run user.MiniMax-Music3-GGUF-BF16
lemonade list
Run it from the terminal:
llama-tts -hf ggml-org/MiniMax-Music3-GGUF -f song.txt --output out.wav
Or with the server, using the /tts endpoint:
llama serve -hf ggml-org/MiniMax-Music3-GGUF
[Tags] section with the music description and a [Lyrics] section.-c 20480.The weights are released under the MiniMax-Music3 Community License, see the license.
This model is automatically converted using https://github.com/ggml-org/convert
8-bit
16-bit
Base model
MiniMaxAI/MiniMax-Music3