Name: music generation model GGUF
Author: mradermacher

Overview

This GGUF-quantized music generation model brings high-fidelity audio synthesis to local environments, eliminating the need for heavy cloud infrastructure. By leveraging the GGUF format, developers can run music generation tasks on consumer-grade hardware with significantly reduced VRAM overhead. It is particularly useful for integrating dynamic soundtracks into game engines, creating procedural audio for apps, or building local creative tools. Compared to full-precision weights, this version offers a streamlined deployment pipeline and faster inference speeds while maintaining the core sonic characteristics of the original architecture. It integrates seamlessly with llama.cpp and other GGUF-compatible runtimes, making it an accessible choice for rapid prototyping and edge deployment.

Highlights

GGUF quantization for low VRAM local execution
Optimized for consumer-grade CPU and GPU hardware
Apache-2.0 license for flexible commercial integration
Ideal for procedural audio and game development
Seamless compatibility with llama.cpp ecosystem

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("mradermacher/music_generation_model-GGUF")
tokenizer = AutoTokenizer.from_pretrained("mradermacher/music_generation_model-GGUF")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download mradermacher/music_generation_model-GGUF

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download mradermacher/music_generation_model-GGUF config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('mradermacher/music_generation_model-GGUF')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/mradermacher/music_generation_model-GGUF

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/mradermacher/music_generation_model-GGUF

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('mradermacher/music_generation_model-GGUF')
tokenizer = AutoTokenizer.from_pretrained('mradermacher/music_generation_model-GGUF')

Full Documentation

来源: HuggingFace

---
base_model: nagayama0706/music_generation_model
language:

en

library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:

merge

mergekit

lazymergekit

TheBloke/openchat_3.5-GPTQ

asigalov61/Allegro-Music-Transformer

---

About

static quants of https://huggingface.co/nagayama0706/music_generation_model

weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| GGUF | Q2_K | 2.8 | |
| GGUF | Q3_K_S | 3.3 | |
| GGUF | Q3_K_M | 3.6 | lower quality |
| GGUF | Q3_K_L | 3.9 | |
| GGUF | IQ4_XS | 4.0 | |
| GGUF | Q4_K_S | 4.2 | fast, recommended |
| GGUF | Q4_K_M | 4.5 | fast, recommended |
| GGUF | Q5_K_S | 5.1 | |
| GGUF | Q5_K_M | 5.2 | |
| GGUF | Q6_K | 6.0 | very good quality |
| GGUF | Q8_0 | 7.8 | fast, best quality |
| GGUF | f16 | 14.6 | 16 bpw, overkill |

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

!image.png

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.