thepatch/musicgen-medium-GGUF

musicgen-medium GGUF

GGUF conversion of facebook/musicgen-medium, Meta's MusicGen medium (1.8B parameters), for audiocraft.cpp's native musicgen-server, which runs gary4local's C++ gary service.

Pick one precision of the language model and put it in a folder with the EnCodec and T5 files. If more than one precision is in the folder, the server runs the most precise. Every quantized tensor round-trips against the F16 conversion at cosine 0.9999 or better for Q8_0 and 0.9963 or better for Q4_K_M.

File	Size
musicgen-medium-1.8B-v1.0-F16.gguf	3,508 MiB	F16; the reference
musicgen-medium-1.8B-v1.0-Q8_0.gguf	1,864 MiB	Q8_0 throughout
musicgen-medium-1.8B-v1.0-Q4_K_M.gguf	1,161 MiB	Q4_K, with the FFN down projection, cross-attention K/V, codebook embeddings and output heads at Q6_K
encodec-32khz-v1.0-F32.gguf	221 MiB	MusicGen's 32 kHz EnCodec
t5-base-encoder-0.1B-v1.0-F16.gguf	210 MiB	T5-base text encoder for descriptions

$env:AC_DEVICE = "cuda"
musicgen-server --port 8000 --models-dir C:\path\to\this\folder

The server lists the model in /api/models as facebook/musicgen-medium and accepts that name as model_name, the same routes gary4juce uses with the Python service. See SERVICES.md.

Sources and licensing

• Language model: facebook/musicgen-medium revision d3bd7b00761b78ad7a8a05145ee31e7832e9916c (state_dict.bin), converted to F16 and quantized with audiocraft.cpp's ac-quantize.
• EnCodec: MusicGen's 32 kHz compression model, facebook/encodec_32khz.
• T5 encoder: google-t5/t5-base revision a9723ea7f1b39c1eae772870f3b547bf6ef7e6c1, Apache 2.0.

MusicGen's weights are released by Meta under CC-BY-NC 4.0, and this conversion inherits that license: non-commercial use only. All credit for the model goes to Meta's AudioCraft team (Copet et al., 2023). T5-base is Apache 2.0. Each GGUF records its own source and license in its general.* metadata.