Instructions to use thepatch/acestep-1.5-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use thepatch/acestep-1.5-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir acestep-1.5-mlx thepatch/acestep-1.5-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
ACE-Step 1.5 MLX artifacts
MLX-native decoder weights prepared by The Patch for fast cold loading on Apple silicon. These artifacts are intended for Carey/gary4local's hard-unload workflow: load for one generation job, generate, then release the model and MLX cache.
Important compatibility note
This repository contains optimized ACE-Step decoder and conditioning weights,
not a standalone ACE-Step pipeline. A consumer still needs the matching VAE,
text encoder/tokenizer, scheduler, and runtime code. Tensor names and convolution
layouts are native to Carey's MLXDiTDecoder; they are not a drop-in replacement
for the upstream PyTorch checkpoint.
Available artifacts
| Path | Upstream source | Source revision | Dtype | Tensor data |
|---|---|---|---|---|
MLX/acestep-v15-xl-base-f16 |
ACE-Step/acestep-v15-xl-base |
220c1166efbdd9583eafcb12eb160594bbfcb241 |
FP16 decoder / source-dtype conditioning | 11,611,452,824 bytes |
Each variant directory contains:
- sharded MLX-native safetensors;
- a standard
model.safetensors.index.json; - a
conditioning/component with the 201 decoder-free source tensors andsilence_latent.ptneeded by Carey's conditioning shell; - the exact upstream
config.json; provenance.json, including source revision, source LFS SHA-256 values, converter source hashes, output hashes, tensor counts, and format version.
manifest.json is the machine-readable repository catalog.
Canary validation
The XL-base FP16 canary was exported from the immutable upstream revision shown above and independently validated against the local source checkpoint:
- 628 decoder tensors plus 1 null-conditioning tensor;
- 201 conditioning tensors plus the source silence latent;
- 4 source shards checked;
- all 629 converted decoder tensors and all 201 conditioning tensors exactly equal;
- artifact config, index, safetensors headers, sizes, and SHA-256 values checked;
- validation peak footprint: 6.97 GB with zero swaps on the test run.
The full per-file evidence is in the variant's provenance.json. Consumers should
verify those hashes after download and reject unknown format_version values.
Format contract
format:thepatch-ace-step-mlxformat_version:1- decoder keys use
MLXDiTDecoderparameter names - the null-conditioning tensor is stored as
__acestep__.null_condition_emb - floating-point tensors use the dtype declared by
provenance.json
License and attribution
The upstream model card declares the source checkpoint under the MIT License. This repository preserves that license and identifies the exact upstream model and revision for every artifact. ACE-Step is developed by the ACE-Step project; these conversions are independently prepared by The Patch.
Quantized
Model tree for thepatch/acestep-1.5-mlx
Base model
ACE-Step/acestep-v15-xl-base