AI/EXPLORER
ToolsCategoriesSitesLLMsCompareAI QuizAlternativesPremium
—AI Tools
—Sites & Blogs
—LLMs & Models
—Categories
AI Explorer

Find and compare the best artificial intelligence tools for your projects.

Made within France

Explore

  • ›All tools
  • ›Sites & Blogs
  • ›LLMs & Models
  • ›Compare
  • ›Chatbots
  • ›AI Images
  • ›Code & Dev

Company

  • ›Premium
  • ›About
  • ›Contact
  • ›Blog

Legal

  • ›Legal notice
  • ›Privacy
  • ›Terms

© 2026 AI Explorer·All rights reserved.

HomeLLMsacestep v15 xl turbo bf16

acestep v15 xl turbo bf16

by marcorez8

Open source · 657 downloads · 6 likes

1.1
(6 reviews)AudioAPI & Local
About

ACE-Step v15 XL Turbo BF16 is an AI model specialized in fast, high-quality music generation. With its optimized architecture of 4 billion parameters and accelerated distillation, it produces tracks in just 8 inference steps, balancing speed and sound fidelity. Designed for commercial use, it relies on legally compliant training data, including licensed music, royalty-free works, and audio synthesized from MIDI scores. Its BF16 version significantly reduces memory usage while maintaining nearly identical quality to the original, making it accessible on more modest GPU setups. Ideal for creators, developers, or businesses looking to integrate high-performance music generation into their projects, it stands out for its balance of speed, quality, and legal compliance.

Documentation

ACE-Step 1.5 XL — Turbo (4B DiT) BF16

Project | Hugging Face | ModelScope | Space Demo | Discord | Tech Report

Model Details

This is the BF16 version of ACE-Step/acestep-v15-xl-turbo — the XL (4B) Turbo variant of ACE-Step 1.5. This BF16 conversion reduces memory usage while maintaining near-identical quality to the original model. It is a distillation-accelerated model that generates high-quality audio in just 8 steps, combining the speed of turbo with the quality of the 4B architecture.

XL Architecture

ParameterValue
DiT Decoder hidden_size2560
DiT Decoder layers32
DiT Decoder attention heads32
Encoder hidden_size2048
Encoder layers8
Total params~4B
Weights size (bf16)~7.5 GB
Inference steps8 (no CFG, distilled)

GPU Requirements

VRAMSupport
≥8 GBWith CPU offload + INT8 quantization
≥12 GBWith CPU offload
≥16 GBWithout offload (recommended)
≥20 GBFull quality (XL + 4B LM)

All LM models (0.6B / 1.7B / 4B) are fully compatible with XL.

Key Features

  • 💰 Commercial-Ready: Trained on legally compliant datasets. Generated music can be used for commercial purposes.
    • 📚 Safe Training Data: Licensed music, royalty-free/public domain, and synthetic (MIDI-to-Audio) data.
      • ⚡ Fast: 8-step inference — the fastest XL variant.
        • 🔮 Higher Quality: 4B parameters provide richer audio quality than 2B turbo.

          • 🧠 BF16 Precision: Converted to BF16 for reduced VRAM usage and faster inference, with negligible quality loss.

          • Quick Start

        • Bash
          # Install ACE-Step
          git clone https://github.com/ace-step/ACE-Step-1.5.git
          cd ACE-Step-1.5
          pip install -e .
          
          # Download this model
          huggingface-cli download marcorez8/acestep-v15-xl-turbo-bf16 --local-dir ./checkpoints/acestep-v15-xl-turbo-bf16
          
          # Run with Gradio UI
          python acestep --config-path acestep-v15-xl-turbo-bf16
          

          Model Zoo

          XL (4B) DiT Models

          DiT ModelCFGStepsQualityDiversityTasksHugging FaceModelScope
          acestep-v15-xl-base✅50HighHighAll (extract, lego, complete)LinkLink
          acestep-v15-xl-sft✅50Very HighMediumStandardLinkLink
          acestep-v15-xl-turbo❌8Very HighMediumStandardLinkLink
          acestep-v15-xl-turbo-bf16❌8Very HighMediumStandardThis repo—

          LM Models (all compatible with XL)

          LM ModelParamsAudio UnderstandingCompositionHugging FaceModelScope
          acestep-5Hz-lm-0.6B0.6BMediumMediumLinkLink
          acestep-5Hz-lm-1.7B1.7BMediumMediumIncluded in mainIncluded in main
          acestep-5Hz-lm-4B4BStrongStrongLinkLink

          Acknowledgements

          This project is co-led by ACE Studio and StepFun. The BF16 conversion was done by marcorez8 to make the model more accessible to the community.

          Citation

          BibTeX
          @misc{gong2026acestep,
            title={ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generation},
            author={Junmin Gong, Yulin Song, Wenxiao Zhao, Sen Wang, Shengyuan Xu, Jing Guo},
            howpublished={\url{https://github.com/ace-step/ACE-Step-1.5}},
            year={2026},
            note={GitHub repository}
          }
          

Capabilities & Tags
transformerssafetensorsacestepfeature-extractionaudiomusictext2musiccustom_codebf16text-to-audio
Links & Resources
Specifications
CategoryAudio
AccessAPI & Local
LicenseOpen Source
PricingOpen Source
Rating
1.1

Try acestep v15 xl turbo bf16

Access the model directly