---
title: ACE-Step-1.5-turbo-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/ACE-Step-1.5-turbo-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/ACE-Step-1.5-turbo-bf16.md"
repository: mlx-community/ACE-Step-1.5-turbo-bf16
last_updated: 2026-10-28
license: mit
model_type:
  - acestep
architectures:
  - AceStepConditionGenerationModel
base_model:
  - ACE-Step/Ace-Step1.5
base_model_relation: finetune
parameters: 2.4B
tensor_type:
  - BF16
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 8
stars: 0
tags:
  - mlx
  - audio
  - music
  - text2music
  - ace-step
---

# ACE-Step-1.5-turbo-bf16

> ACE-Step-1.5-turbo-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/ACE-Step-1.5-turbo-bf16

mlx-community/ACE-Step-1.5-turbo-bf16 是 ModelScope 魔搭社区上的 2.4B 参数机器学习模型，采用 mit 许可，基于 ACE-Step/Ace-Step1.5 构建。

- **Repository**: mlx-community/ACE-Step-1.5-turbo-bf16
- **License**: mit
- **Parameters**: 2.4B
- **Base model**: ACE-Step/Ace-Step1.5
- **Tags**: mlx, audio, music, text2music, ace-step
- **Downloads**: 8
- **Stars**: 0
- **Last updated**: 2026-10-28

Source: https://www.modelscope.cn/models/mlx-community/ACE-Step-1.5-turbo-bf16

---

# mlx-community/ACE-Step-1.5-turbo-bf16

ACE-Step 1.5 turbo (DiT + condition encoder + FSQ tokenizer / detokenizer) — MLX, bf16. Converted from [ACE-Step/Ace-Step1.5](https://huggingface.co/ACE-Step/Ace-Step1.5) @ `19671f4` by the converter of
[xocialize/mlx-ace-step-swift](https://github.com/xocialize/mlx-ace-step-swift) (`Tools/convert/convert.py`, mlx 0.32.4), a full
port of [ace-step/ACE-Step-1.5](https://github.com/ace-step/ACE-Step-1.5) @ `ca1e85f` to Swift-MLX.

## What is in the bundle

`acestep-v15-turbo` of ACE-Step 1.5 in MLX layout, bf16: the 2 B flow-matching DiT (24 layers, alternating sliding-128 /
full attention, adaLN, cross-attention), the condition encoder (lyric encoder 8 layers, timbre encoder 4 layers, text projector),
the FSQ audio tokenizer (attention pooler + ResidualFSQ, levels [8, 8, 8, 5, 5, 5]) and the 2-layer detokenizer — 677 tensors,
keys as in the checkpoint except `decoder.proj_in.1` / `decoder.proj_out.1` → `decoder.proj_in` / `decoder.proj_out` with the
convolutions in MLX's `[out, k, in]` layout; plus `silence_latent.safetensors` (`[15000, 64]` fp32, the silence latent the
pipeline pads and references with). `config.json` is the checkpoint's with an `mlx_ace_step` provenance block.

## Licence

MIT. The Hugging Face repository `ACE-Step/Ace-Step1.5` ships no LICENSE file; its model-card tag and README state MIT and the [GitHub LICENSE](https://github.com/ace-step/ACE-Step-1.5/blob/main/LICENSE) (Copyright (c) 2026 ACEStep) is the controlling text.

The full notice travels with the bundle as `NOTICE`; `LICENSE` is the MIT text. Nothing in the weights is modified beyond the
layout conversion (key prefix / conv layout / weight-norm folding) — the converter `Tools/convert/convert.py` in
[xocialize/mlx-ace-step-swift](https://github.com/xocialize/mlx-ace-step-swift) is gated bit-equal against upstream's own
`dit_convert.py` / `vae_convert.py` (its `MEASUREMENTS.md` §V1).

## Use

Every tier of the Swift package loads four bundles — the turbo DiT, one planner, the text encoder and the VAE — and this bundle
is one of them. The planner choices: `ACE-Step-1.5-planner-1.7B-8bit` for `.int8` (the default), `-4bit` for `.int4`, `-bf16` for
`.bf16` / `.fp32`, and `ACE-Step-1.5-planner-0.6B-bf16` for the lite planner on any tier. The package,
[xocialize/mlx-ace-step-swift](https://github.com/xocialize/mlx-ace-step-swift), runs ACE-Step 1.5 on Apple Silicon through
[MLX Swift](https://github.com/ml-explore/mlx-swift) and plugs into [MLXEngine](https://github.com/xocialize/mlx-engine-swift) on the
`music` capability (caption + lyrics → a 48 kHz stereo song; reference-audio timbre; cover / repaint / extend of a source clip;
LRC timestamps). The package's `ACEStepConfiguration` names these repos and the engine materialises them; the parity gates
against the upstream oracle (fp32, TF32 off) are recorded in the package's `MEASUREMENTS.md`.

```swift
let engine = MLXServeEngine()
let id = try await engine.register(ACEStepPackage.registration, configuration: ACEStepConfiguration())   // the .int8 default
try await engine.prepare(.music, package: id)
let song = try await engine.run(MusicRequest(caption: "…", lyrics: "[Verse]\n…", durationSeconds: 120, seed: 7), package: id)
```


Upstream: [ACE-Step/Ace-Step1.5](https://huggingface.co/ACE-Step/Ace-Step1.5) @ `19671f4` (weights),
[ace-step/ACE-Step-1.5](https://github.com/ace-step/ACE-Step-1.5) @ `ca1e85f` (code) — ACE Studio + StepFun,
[tech report](https://arxiv.org/abs/2602.00744).