Text-to-Audio
Diffusers
GGUF
PyTorch
English
llama-cpp
llama-tts
music-generation
text-to-music
sglang-omni
minimax
Instructions to use prithivMLmods/MiniMax-Music3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use prithivMLmods/MiniMax-Music3-GGUF with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("prithivMLmods/MiniMax-Music3-GGUF", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use prithivMLmods/MiniMax-Music3-GGUF 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 prithivMLmods/MiniMax-Music3-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf prithivMLmods/MiniMax-Music3-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf prithivMLmods/MiniMax-Music3-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf prithivMLmods/MiniMax-Music3-GGUF:Q4_K_M
Build from source code
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 prithivMLmods/MiniMax-Music3-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf prithivMLmods/MiniMax-Music3-GGUF:Q4_K_M
Use Docker
docker model run hf.co/prithivMLmods/MiniMax-Music3-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use prithivMLmods/MiniMax-Music3-GGUF with Ollama:
ollama run hf.co/prithivMLmods/MiniMax-Music3-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use prithivMLmods/MiniMax-Music3-GGUF with Docker Model Runner:
docker model run hf.co/prithivMLmods/MiniMax-Music3-GGUF:Q4_K_M
- Lemonade
How to use prithivMLmods/MiniMax-Music3-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull prithivMLmods/MiniMax-Music3-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.MiniMax-Music3-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,10 @@ base_model:
|
|
| 3 |
- MiniMaxAI/MiniMax-Music3
|
| 4 |
---
|
| 5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
## Run with llama.cpp
|
| 7 |
|
| 8 |
### Install dependencies and clone llama.cpp
|
|
@@ -135,3 +139,9 @@ The generated audio file will be saved at:
|
|
| 135 |
| MiniMax-Music3.Q6_K.gguf | Q6_K | 7.05 GB | [Link](https://huggingface.co/prithivMLmods/MiniMax-Music3-GGUF/blob/main/MiniMax-Music3.Q6_K.gguf) | Very high quality, near perfect, *recommended*. |
|
| 136 |
| MiniMax-Music3.Q8_0.gguf | Q8_0 | 9.13 GB | [Link](https://huggingface.co/prithivMLmods/MiniMax-Music3-GGUF/blob/main/MiniMax-Music3.Q8_0.gguf) | Extremely high quality, generally unneeded but max available standard quant. |
|
| 137 |
| MiniMax-Music3.mmproj-bf16.gguf | mmproj-bf16 | 6.64 GB | [Link](https://huggingface.co/prithivMLmods/MiniMax-Music3-GGUF/blob/main/MiniMax-Music3.mmproj-bf16.gguf) | Multimodal projection file in BF16 format. Used for audio/music capabilities. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
- MiniMaxAI/MiniMax-Music3
|
| 4 |
---
|
| 5 |
|
| 6 |
+
# **MiniMax-Music3-GGUF**
|
| 7 |
+
|
| 8 |
+
> **MiniMax Music 3** is an open-weights text-to-music generation model from MiniMax AI that creates complete, structurally coherent songs up to five minutes long in 32 kHz, 16-bit stereo WAV format. Conditioned on section-tagged lyrics (such as `[Verse]` and `[Chorus]`) and detailed style descriptions covering metadata, vocals, and arrangement, it uses a hierarchical Hybrid-LM architecture pairing a Qwen3-initialized **8B Global LLM** for long-range musical structure with a **0.6B Local LLM** for frame-level acoustic detail. Instead of decoding directly from discrete Residual Vector Quantization (RVQ) tokens, the system fuses the hidden states of both language models and synthesizes high-fidelity audio through a **2.4B Flow Matching** module and **Flow-VAE** decoder, supporting deployment via SGLang-Omni, Hugging Face `diffusers`, and ComfyUI—even scaling down to 8 GB VRAM GPUs with layer offloading.
|
| 9 |
+
|
| 10 |
## Run with llama.cpp
|
| 11 |
|
| 12 |
### Install dependencies and clone llama.cpp
|
|
|
|
| 139 |
| MiniMax-Music3.Q6_K.gguf | Q6_K | 7.05 GB | [Link](https://huggingface.co/prithivMLmods/MiniMax-Music3-GGUF/blob/main/MiniMax-Music3.Q6_K.gguf) | Very high quality, near perfect, *recommended*. |
|
| 140 |
| MiniMax-Music3.Q8_0.gguf | Q8_0 | 9.13 GB | [Link](https://huggingface.co/prithivMLmods/MiniMax-Music3-GGUF/blob/main/MiniMax-Music3.Q8_0.gguf) | Extremely high quality, generally unneeded but max available standard quant. |
|
| 141 |
| MiniMax-Music3.mmproj-bf16.gguf | mmproj-bf16 | 6.64 GB | [Link](https://huggingface.co/prithivMLmods/MiniMax-Music3-GGUF/blob/main/MiniMax-Music3.mmproj-bf16.gguf) | Multimodal projection file in BF16 format. Used for audio/music capabilities. |
|
| 142 |
+
|
| 143 |
+
## llama.cpp
|
| 144 |
+
|
| 145 |
+
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp
|
| 146 |
+
|
| 147 |
+
Quantized using llama.cpp by [prithivMLmods](https://huggingface.co/prithivMLmods).
|