acestep-v15-xl-base
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-xl-baseNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
acestep-v15-xl-base is an open-weight audio and music generation model published by ACE-Step on Hugging Face in April 2026, with 5B parameters under the mit license.
Among the 23 audio and music generation models in this directory it ranks 20th by monthly Hugging Face downloads, and 1 of the others are larger.
HardwareLink to this section
Unquantized FP16 weights take about 10 GB; 8-bit brings that to ~5 GB and 4-bit (Q4_K_M) to ~3 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
- YuE2-3B - 3.6B, 20,330 downloads/month
- acestep-5Hz-lm-4B - 4.2B, 18,030 downloads/month
- acestep-v15-xl-sft - 5B, 11,148 downloads/month
- acestep-v15-xl-turbo - 5B, 10,640 downloads/month
- HeartMuLa-oss-3B-happy-new-year - 3.9B, 3,229 downloads/month
PopularityLink to this section
acestep-v15-xl-base was downloaded 3,113 times on Hugging Face in the last month (15,851 all-time) and has 116 likes.
Run it locallyLink to this section
Weights and usage instructions are on the ACE-Step/acestep-v15-xl-base 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-xl-base need?
acestep-v15-xl-base with 5B parameters needs approximately 3 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is acestep-v15-xl-base better than other ACE-Step models?
acestep-v15-xl-base has 5B parameters - a strong choice for audio-generation, music-generation.
What license is acestep-v15-xl-base under?
acestep-v15-xl-base is released under the mit license, making it suitable for most commercial and personal projects.
What hardware runs acestep-v15-xl-base well?
With 5B parameters, acestep-v15-xl-base 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-xl-base?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~4 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
What models compete with acestep-v15-xl-base?
acestep-v15-xl-base 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