Text-to-Audio
MLX
Diffusers
Safetensors
minimax_music3
apple-silicon
macos
minimax
minimax-music3
audio-generation
generative-audio
music-generation
text-to-music
local-inference
Instructions to use appautomaton/MiniMax-Music3-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use appautomaton/MiniMax-Music3-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MiniMax-Music3-MLX appautomaton/MiniMax-Music3-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "components": { | |
| "condition_encoder": { | |
| "files": [ | |
| { | |
| "dtypes": [], | |
| "path": "condition_encoder/config.json", | |
| "sha256": "611ba86f32561013f9beb20bc180d0afd671e27906be996830f0bf179886a209", | |
| "size": 203, | |
| "source_path": "condition_encoder/config.json", | |
| "source_sha256": "1cdea3f36506719128ae4a29cdfff74b1134e607eb4a504ce6d810568fac8263", | |
| "tensor_count": 0 | |
| }, | |
| { | |
| "dtypes": [ | |
| "F32" | |
| ], | |
| "path": "condition_encoder/diffusion_pytorch_model.safetensors", | |
| "sha256": "648708da1db6476fd4372c2b5b139bff1e06fb0a6e9c4541ab50305b8fe6dc2f", | |
| "size": 100671956, | |
| "source_path": "condition_encoder/diffusion_pytorch_model.safetensors", | |
| "source_sha256": "83179c5eaa9a68a370affe0c1b96c2179f659ea4175666b31071490a202c2a4d", | |
| "tensor_count": 4 | |
| } | |
| ] | |
| }, | |
| "language_model": { | |
| "files": [ | |
| { | |
| "dtypes": [], | |
| "path": "language_model/config.json", | |
| "sha256": "34ded58fcd5e8181557f1417e76af9f3e95109a5ce113a4771fd16f8625b53c0", | |
| "size": 1596, | |
| "source_path": "language_model/config.json", | |
| "source_sha256": "34ded58fcd5e8181557f1417e76af9f3e95109a5ce113a4771fd16f8625b53c0", | |
| "tensor_count": 0 | |
| }, | |
| { | |
| "dtypes": [], | |
| "path": "language_model/generation_config.json", | |
| "sha256": "c0f7c1612e174a7bdec9548464a7bf031a0292587033228e6767fb9e5dc367cd", | |
| "size": 158, | |
| "source_path": "language_model/generation_config.json", | |
| "source_sha256": "c0f7c1612e174a7bdec9548464a7bf031a0292587033228e6767fb9e5dc367cd", | |
| "tensor_count": 0 | |
| }, | |
| { | |
| "dtypes": [ | |
| "BF16" | |
| ], | |
| "path": "language_model/model-00001-of-00004.safetensors", | |
| "sha256": "1e95924a158b45b67cfad04fa0f0a352e5a263e69338734d7c1d558be776cc98", | |
| "size": 4910103856, | |
| "source_path": "language_model/model-00001-of-00004.safetensors", | |
| "source_sha256": "1e95924a158b45b67cfad04fa0f0a352e5a263e69338734d7c1d558be776cc98", | |
| "tensor_count": 96 | |
| }, | |
| { | |
| "dtypes": [ | |
| "BF16" | |
| ], | |
| "path": "language_model/model-00002-of-00004.safetensors", | |
| "sha256": "fde2d335eef7eafa268d35e53d4b040ee51d2f3fa727f9855b4c97d88a2892da", | |
| "size": 4915960352, | |
| "source_path": "language_model/model-00002-of-00004.safetensors", | |
| "source_sha256": "fde2d335eef7eafa268d35e53d4b040ee51d2f3fa727f9855b4c97d88a2892da", | |
| "tensor_count": 142 | |
| }, | |
| { | |
| "dtypes": [ | |
| "BF16" | |
| ], | |
| "path": "language_model/model-00003-of-00004.safetensors", | |
| "sha256": "6549a831637ab678a573047e7fa8fdf966998c4f45330e6eb7573d67f7b9b4c6", | |
| "size": 4983068496, | |
| "source_path": "language_model/model-00003-of-00004.safetensors", | |
| "source_sha256": "6549a831637ab678a573047e7fa8fdf966998c4f45330e6eb7573d67f7b9b4c6", | |
| "tensor_count": 140 | |
| }, | |
| { | |
| "dtypes": [ | |
| "BF16" | |
| ], | |
| "path": "language_model/model-00004-of-00004.safetensors", | |
| "sha256": "a1c9865f357b64d3ae9f428fb98a844831e5a0aee9ed17b19bd7f7be32b964a9", | |
| "size": 2359864688, | |
| "source_path": "language_model/model-00004-of-00004.safetensors", | |
| "source_sha256": "a1c9865f357b64d3ae9f428fb98a844831e5a0aee9ed17b19bd7f7be32b964a9", | |
| "tensor_count": 21 | |
| }, | |
| { | |
| "dtypes": [], | |
| "path": "language_model/model.safetensors.index.json", | |
| "sha256": "a8bf9de1e8c0d680f39730a127d74445b4abf505623bd91d5ed4f97c0869cc2a", | |
| "size": 32914, | |
| "source_path": "language_model/model.safetensors.index.json", | |
| "source_sha256": "a8bf9de1e8c0d680f39730a127d74445b4abf505623bd91d5ed4f97c0869cc2a", | |
| "tensor_count": 0 | |
| } | |
| ] | |
| }, | |
| "root": { | |
| "files": [ | |
| { | |
| "dtypes": [], | |
| "path": "LICENSE", | |
| "sha256": "b21d12df2adae59dad3fcf80c1d81492654c662342f497d9a9770198c9317e58", | |
| "size": 7373, | |
| "source_path": "LICENSE", | |
| "source_sha256": "b21d12df2adae59dad3fcf80c1d81492654c662342f497d9a9770198c9317e58", | |
| "tensor_count": 0 | |
| }, | |
| { | |
| "dtypes": [], | |
| "path": "config.json", | |
| "sha256": "1ffcff67d916d5519d1ef9a36853232ee6bcb7e14a936623c4e85559f5dce106", | |
| "size": 107, | |
| "source_path": "config.json", | |
| "source_sha256": "1ffcff67d916d5519d1ef9a36853232ee6bcb7e14a936623c4e85559f5dce106", | |
| "tensor_count": 0 | |
| } | |
| ] | |
| }, | |
| "rvq_depth_decoder": { | |
| "files": [ | |
| { | |
| "dtypes": [], | |
| "path": "rvq_depth_decoder/config.json", | |
| "sha256": "2c34c93c0ad15699f96e24f2a70d78924bd58cae7942b64b04d8a0e6f3978cd3", | |
| "size": 186, | |
| "source_path": "rvq_depth_decoder/config.json", | |
| "source_sha256": "b38c7f72d4b2fa8667442071f9e4a63ca5a7b5d0859e5e64ee7f79c4bc64520c", | |
| "tensor_count": 0 | |
| }, | |
| { | |
| "dtypes": [ | |
| "BF16" | |
| ], | |
| "path": "rvq_depth_decoder/diffusion_pytorch_model.safetensors", | |
| "sha256": "80e86ab006bb5c8d4f223205045035a1c77b2bb9c3be9a86d7e740bbafe5ddf0", | |
| "size": 1292055248, | |
| "source_path": "rvq_depth_decoder/diffusion_pytorch_model.safetensors", | |
| "source_sha256": "80e86ab006bb5c8d4f223205045035a1c77b2bb9c3be9a86d7e740bbafe5ddf0", | |
| "tensor_count": 47 | |
| } | |
| ] | |
| }, | |
| "scheduler": { | |
| "files": [ | |
| { | |
| "dtypes": [], | |
| "path": "scheduler/scheduler_config.json", | |
| "sha256": "01eb28ee93a8283713ae2dde5f4e1e008441ccb6ffa4aca2637f3da02966b6b7", | |
| "size": 392, | |
| "source_path": "scheduler/scheduler_config.json", | |
| "source_sha256": "b544466124aab333da4874417da0168610067e9c9ff95fcb63d749e4bf891d99", | |
| "tensor_count": 0 | |
| } | |
| ] | |
| }, | |
| "tokenizer": { | |
| "files": [ | |
| { | |
| "dtypes": [], | |
| "path": "tokenizer/chat_template.jinja", | |
| "sha256": "a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8", | |
| "size": 4168, | |
| "source_path": "tokenizer/chat_template.jinja", | |
| "source_sha256": "a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8", | |
| "tensor_count": 0 | |
| }, | |
| { | |
| "dtypes": [], | |
| "path": "tokenizer/tokenizer.json", | |
| "sha256": "b1537fa9e59a537276ecbc2e12d0438edff635a1f4a4948e679774b5feb3e610", | |
| "size": 11423801, | |
| "source_path": "tokenizer/tokenizer.json", | |
| "source_sha256": "b1537fa9e59a537276ecbc2e12d0438edff635a1f4a4948e679774b5feb3e610", | |
| "tensor_count": 0 | |
| }, | |
| { | |
| "dtypes": [], | |
| "path": "tokenizer/tokenizer_config.json", | |
| "sha256": "1689852cc9c45010de040c8302a8acdc0d2c4c6c740dd7e9dd0a8c704e16eada", | |
| "size": 377, | |
| "source_path": "tokenizer/tokenizer_config.json", | |
| "source_sha256": "1689852cc9c45010de040c8302a8acdc0d2c4c6c740dd7e9dd0a8c704e16eada", | |
| "tensor_count": 0 | |
| } | |
| ] | |
| }, | |
| "transformer": { | |
| "files": [ | |
| { | |
| "dtypes": [], | |
| "path": "transformer/config.json", | |
| "sha256": "2bdb9ba2ace20c423bb6ddc5bfb1de242ce6544e515b926e20bf462fa211b9dc", | |
| "size": 203, | |
| "source_path": "transformer/config.json", | |
| "source_sha256": "f60856be934127a8b8223510aff2e38a9efd8bbdbc230c3d3339b96e2cb12f00", | |
| "tensor_count": 0 | |
| }, | |
| { | |
| "dtypes": [ | |
| "F32" | |
| ], | |
| "path": "transformer/diffusion_pytorch_model-00001-of-00002.safetensors", | |
| "sha256": "62601f15496117f2d4a22b180b70d9943de1b992c3918bf525b7b108a21c7904", | |
| "size": 4959921444, | |
| "source_path": "transformer/diffusion_pytorch_model-00001-of-00002.safetensors", | |
| "source_sha256": "1943baebe93b5d5a57e9e1f603d9cef51a73a55e7a42f52913932dc06dcf10f0", | |
| "tensor_count": 231 | |
| }, | |
| { | |
| "dtypes": [ | |
| "F32" | |
| ], | |
| "path": "transformer/diffusion_pytorch_model-00002-of-00002.safetensors", | |
| "sha256": "b624bd1017e999b2addd7dab6fba9c9af06069c6be05117c7a973ac92c3f79a9", | |
| "size": 4767750858, | |
| "source_path": "transformer/diffusion_pytorch_model-00002-of-00002.safetensors", | |
| "source_sha256": "b2f9e29d241e107e5a281f8b369d6db48eee983917df966c56d7b8dd0bd482c2", | |
| "tensor_count": 210 | |
| }, | |
| { | |
| "dtypes": [], | |
| "path": "transformer/diffusion_pytorch_model.safetensors.index.json", | |
| "sha256": "5a57fc3b98e91ec7f4e9da199b3dc8ce1c67e42824c42bed91c15443c049b991", | |
| "size": 42679, | |
| "source_path": "transformer/diffusion_pytorch_model.safetensors.index.json", | |
| "source_sha256": "5a57fc3b98e91ec7f4e9da199b3dc8ce1c67e42824c42bed91c15443c049b991", | |
| "tensor_count": 0 | |
| } | |
| ] | |
| }, | |
| "vocoder": { | |
| "files": [ | |
| { | |
| "dtypes": [], | |
| "path": "vocoder/config.json", | |
| "sha256": "6d6baefe31c62cc7514eb81300c76f7006c0e3f92069fd64782096ef6356084c", | |
| "size": 171, | |
| "source_path": "vocoder/config.json", | |
| "source_sha256": "4161afd07ba7d5b949e29c8a7a005592259fba73e9110b6ece9dfd38d3489eac", | |
| "tensor_count": 0 | |
| }, | |
| { | |
| "dtypes": [ | |
| "F32" | |
| ], | |
| "path": "vocoder/diffusion_pytorch_model.safetensors", | |
| "sha256": "3e5250ca7a7cddf84e084b7699f0803bb69af0aa17cb67b4ff2756fdb803ff57", | |
| "size": 216639816, | |
| "source_path": "vocoder/diffusion_pytorch_model.safetensors", | |
| "source_sha256": "daf0bf0560ea978ce7b5ec3e82f420a44429efef18bdfbe3c714d55ceffbe934", | |
| "tensor_count": 91 | |
| } | |
| ] | |
| } | |
| }, | |
| "format": "mlx-minimax-music3", | |
| "format_version": 1, | |
| "mapping_version": 1, | |
| "profile": "dense", | |
| "source": { | |
| "repository": "MiniMaxAI/MiniMax-Music3", | |
| "revision": "fbdf52fbaaca799592917417eb05f1899f1255ec" | |
| } | |
| } | |