How to run MusicGen Large locally

Meta · Text → music · 3.3B params · CC-BY-NC-4.0 (non-commercial)

Meta's flagship text-to-music model generating coherent ~30s clips from text, optionally guided by a melody.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 16 GB of VRAM (~16GB for large; medium (1.5B) fits in ~8GB), via AudioCraft / Transformers.
Rent a GPU — from $0.26/hr. Fits RTX 3090 24GB at the direct vendor price ($0 markup) — pay only for the minutes you generate.
Download the weights — free. Open weights at facebook/musicgen-large.

Note: generative-media models are billed per image / per second / per minute on hosted services — not per token. Running locally or on your own rented GPU is usually far cheaper and keeps your data on your machine.

Key facts

Does	Text → music
VRAM to run	~16 GB (~16GB for large; medium (1.5B) fits in ~8GB)
Download	~13 GB
Parameters	3.3B
License	CC-BY-NC-4.0 (non-commercial)
Run with	AudioCraft / Transformers

Get MusicGen Large on Hugging Face →

More voice & audio models

Whisper large-v3 — Speech → text, ~10 GB VRAM
Whisper large-v3-turbo — Speech → text, ~6.0 GB VRAM
Kokoro-82M — Text → speech, ~1.0 GB VRAM
XTTS-v2 — Voice cloning, ~6.0 GB VRAM
Chatterbox — Text → speech, ~8.0 GB VRAM
Parakeet TDT 0.6B v2 — Speech → text, ~4.0 GB VRAM

Browse: all media models · chat / LLM models