StepFun · 3D · 4.8B parameters · Apache-2.0
Step1X-3D
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.
Parameters4.8Bdense
Category3Dsized on weights + headroom
Checkpoint20 GBBF16, as published
LicenseApache-2.0check before commercial use
ReleasedMay 13, 2025documented date
Smallest configuration · FP8 / INT8
1× RTX 306012 GB VRAM · 48% used
- Per hour
- $0.04
- Per month
- $26
- Cheapest at
Vast.ai
What is documented about Step1X-3D
news checked 2026-10-27Geometry 1.3B + texture 3.5B (folders 7.25 GB + 3.60 GB; label variant 8.78 GB). No newer StepFun 3D release found.
- https://huggingface.co/stepfun-ai/Step1X-3D
- https://huggingface.co/api/models/stepfun-ai/Step1X-3D?blobs=true
- https://github.com/stepfun-ai/Step1X-3D
How much VRAM it needs
Weights plus 20% runtime overhead. For 3d models, activations also depend on resolution, clip length and batch size; the per-GPU estimates below give the practical configuration.
| Precision | Weights | Weights + headroom |
|---|---|---|
| BF16published checkpoint | 20 GB | 24 GB |
| FP8 / INT8estimated | 5 GB | 6 GB |
| INT4 / MXFP4estimated | 3 GB | 4 GB |
Cross-checked on Hugging Face Oct 28, 2026: repository read, 19.6 GB of weight files. Method: weights as published at the native precision, verified on Hugging Face 2026-10-28; other precisions estimated at 1 (8-bit) and 0.6 (4-bit) bytes per parameter; × 1.2 runtime headroom; KV cache not added (architecture not readable).
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 | 48% | $0.04 | $26 | |
| RTX A2000 | 1× 12 GB12 GB total | 48% | $0.04 | $26 | |
| GTX 1660 Ti | 1× 6 GB6 GB total | 96% tight | $0.04 | $26 | |
| Tesla P4 | 1× 8 GB8 GB total | 72% | $0.04 | $29 | |
| T4 | 1× 16 GB16 GB total | 36% | $0.04 | $29 | |
| GTX 1060 | 1× 6 GB6 GB total | 96% tight | $0.04 | $30 | |
| GTX 1660 | 1× 6 GB6 GB total | 96% tight | $0.04 | $30 | |
| Tesla P40 | 1× 24 GB24 GB total | 24% | $0.04 | $30 | |
| GTX Titan X | 1× 12 GB12 GB total | 48% | $0.04 | $31 | |
| Titan Xp | 1× 12 GB12 GB total | 48% | $0.04 | $31 | |
| GTX 1080 | 1× 8 GB8 GB total | 72% | $0.04 | $32 | |
| Tesla P100 | 1× 16 GB16 GB total | 36% | $0.04 | $33 | |
| RTX 2060 | 1× 6 GB6 GB total | 96% tight | $0.04 | $33 | |
| GTX 1070 | 1× 8 GB8 GB total | 72% | $0.05 | $36 | |
| GTX 1660 Super | 1× 6 GB6 GB total | 96% tight | $0.05 | $38 | |
| Quadro P4000 | 1× 8 GB8 GB total | 72% | $0.06 | $40 | |
| RTX 2070 | 1× 8 GB8 GB total | 72% | $0.06 | $41 | |
| RTX 3060 Ti | 1× 8 GB8 GB total | 72% | $0.06 | $41 | |
| RTX 2060 Super | 1× 8 GB8 GB total | 72% | $0.06 | $41 | |
| Quadro P2000 | 2× 5 GB10 GB total | 58% | $0.06 | $41 | |
| GTX 1070 Ti | 1× 8 GB8 GB total | 72% | $0.06 | $44 | |
| RTX 2070 Super | 1× 8 GB8 GB total | 72% | $0.06 | $44 | |
| RTX 3070 | 1× 8 GB8 GB total | 72% | $0.06 | $44 | |
| RTX 4060 | 1× 8 GB8 GB total | 72% | $0.06 | $45 | |
| The 24 cheapest of 107 GPU types that fit. Every GPU, any precision and context, in the finder | |||||
