ACE-Step models
1 ACE-Step model from ACE-Step on Hugging Face, from 4.2B to 4.2B parameters, published by ACE-Step in BF16, with a 40K-token context. The smallest official model, acestep-5Hz-lm-4B, needs about 9.4 GB of VRAM at its published precision; the cheapest live fit is RTX 3060 at $0.110/hr.
Pick a size
One row per official ACE-Step size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| acestep-5Hz-lm-4B | 4.2B | 9.4 GB | 4.7 GB | 2.3 GB | RTX 3060 | $0.110/hr | 4.5 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| acestep-5Hz-lm-4B | 4.2B | BF16 | 9.4 GB | RTX 3060 | $0.110/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.