acestep-v15-xl-turbo
Needs 6 GB at FP8 / INT8. The smallest real configuration today is 1× RTX 3060 at Vast.ai, $0.04 per hour, about $26 a month at 730 hours.
- Per hour
- $0.04
- Per month
- $26
- Cheapest at
Vast.ai
How much VRAM it needs
Weights plus 20% runtime overhead. For music models, activations also depend on resolution, clip length and batch size; the per-GPU estimates below give the practical configuration.
| Precision | Weights | Weights + headroom |
|---|---|---|
| FP32published checkpoint | 20 GB | 24 GB |
| FP8 / INT8estimated | 5 GB | 6 GB |
| INT4 / MXFP4estimated | 3 GB | 4 GB |
What it costs to run, GPU by GPU
The fewest GPUs of one type whose total memory fits the model at short context, priced from the cheapest eligible on-demand offer for exactly that count (45-day window, newest reading per provider), with the next providers beside it. Monthly = 730 hours.
| GPU | Smallest config | VRAM used | $ / hour | $ / month | Cheapest at |
|---|---|---|---|---|---|
| RTX 3060Best fit | 1× 12 GB12 GB total | 50% | $0.04 | $26 | |
| GTX 1660 | 1× 6 GB6 GB total | 100% tight | $0.04 | $26 | |
| RTX A2000 | 1× 12 GB12 GB total | 50% | $0.04 | $26 | |
| GTX 1660 Ti | 1× 6 GB6 GB total | 100% tight | $0.04 | $26 | |
| Tesla P4 | 1× 8 GB8 GB total | 75% | $0.04 | $29 | |
| T4 | 1× 16 GB16 GB total | 37% | $0.04 | $29 | |
| GTX 1060 | 1× 6 GB6 GB total | 100% tight | $0.04 | $30 | |
| Tesla P40 | 1× 24 GB24 GB total | 25% | $0.04 | $30 | |
| GTX Titan X | 1× 12 GB12 GB total | 50% | $0.04 | $31 | |
| Titan Xp | 1× 12 GB12 GB total | 50% | $0.04 | $31 | |
| GTX 1080 | 1× 8 GB8 GB total | 75% | $0.04 | $32 | |
| Tesla P100 | 1× 16 GB16 GB total | 37% | $0.04 | $33 | |
| RTX 2060 | 1× 6 GB6 GB total | 100% tight | $0.04 | $33 | |
| GTX 1070 | 1× 8 GB8 GB total | 75% | $0.05 | $36 | |
| GTX 1660 Super | 1× 6 GB6 GB total | 100% tight | $0.05 | $38 | |
| RTX 4060 | 1× 8 GB8 GB total | 75% | $0.05 | $40 | |
| RTX 2070 | 1× 8 GB8 GB total | 75% | $0.06 | $41 | |
| RTX 3060 Ti | 1× 8 GB8 GB total | 75% | $0.06 | $41 | |
| RTX 2060 Super | 1× 8 GB8 GB total | 75% | $0.06 | $41 | |
| Quadro P2000 | 2× 5 GB10 GB total | 60% | $0.06 | $41 | |
| GTX 1070 Ti | 1× 8 GB8 GB total | 75% | $0.06 | $44 | |
| RTX 2070 Super | 1× 8 GB8 GB total | 75% | $0.06 | $44 | |
| RTX 3070 | 1× 8 GB8 GB total | 75% | $0.06 | $44 | |
| GTX 1080 Ti | 1× 11 GB11 GB total | 54% | $0.06 | $45 | |
| The 24 cheapest of 107 GPU types that fit. Every GPU, any precision and context, in the finder | |||||
Estimated speed, in s per 3-min track
Music. Speed estimated from memory bandwidth and model size, never measured. The cost per 1,000 tracks is an estimate at the prices read on Oct 4, 2026; it is not recomputed here.
| GPU | Cards | Precision | s per 3-min track | per 1,000 tracks · estimate |
|---|---|---|---|---|
| RTX 4090 | 1 | BF16 | 7.4 | $0.471 |
| RTX 5090 | 1 | BF16 | 5.6 | $0.750 |
| L40S | 1 | BF16 | 7.2 | $1.09 |
| MI300X | 1 | BF16 | 2.7 | $1.24 |
| H100 PCIe | 1 | BF16 | 3.7 | $1.41 |
| H100 SXM | 1 | BF16 | 2.8 | $1.46 |
| RTX PRO 6000 | 1 | BF16 | 5.0 | $1.60 |
| B200 | 1 | BF16 | 1.4 | $1.61 |
| A100 80GB | 1 | BF16 | 6.6 | $1.75 |
| H200 | 1 | BF16 | 2.6 | $1.83 |
