acestep-v15-sft
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve ACE-Step/acestep-v15-sftNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
acestep-v15-sft is an open-weight audio and music generation model published by ACE-Step on Hugging Face in January 2026, with 2.4B parameters under the mit license.
Among the 23 audio and music generation models in this directory it ranks 15th by monthly Hugging Face downloads, and 8 of the others are larger.
HardwareLink to this section
Unquantized FP16 weights take about 5 GB; 8-bit brings that to ~3 GB and 4-bit (Q4_K_M) to ~1 GB, before activations and any context or image buffers. A 12 GB consumer card holds it at 4-bit; FP16 needs a 24 GB card such as an RTX 4090. Check exact numbers for your card with the VRAM calculator.
Similar audio and music generation modelsLink to this section
- stable-audio-3-medium - 2.3B, 136,424 downloads/month
- stable-audio-3-medium-base - 2.3B, 11,196 downloads/month
- acestep-v15-base - 2.4B, 6,439 downloads/month
- MiniMax-Music3 - 2.4B, 5,300 downloads/month
- musicgen-stereo-medium - 2B, 4,180 downloads/month
PopularityLink to this section
acestep-v15-sft was downloaded 6,178 times on Hugging Face in the last month (31,453 all-time) and has 57 likes.
Run it locallyLink to this section
Weights and usage instructions are on the ACE-Step/acestep-v15-sft model card; it loads with Hugging Face Transformers.
Local runtimes that fit this model:
- transformers - the reference Python library most model cards target
PaperLink to this section
Frequently asked
Quick answers to common questions
How much VRAM does acestep-v15-sft need?
acestep-v15-sft with 2.4B parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is acestep-v15-sft better than other ACE-Step models?
acestep-v15-sft has 2.4B parameters - a strong choice for audio-generation, music-generation.
What license is acestep-v15-sft under?
acestep-v15-sft is released under the mit license, making it suitable for most commercial and personal projects.
What hardware runs acestep-v15-sft well?
With 2.4B parameters, acestep-v15-sft requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for acestep-v15-sft?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~2 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
What models compete with acestep-v15-sft?
acestep-v15-sft competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec