What GPU do I need to run stepfun-ai/step3?
321.0B parameters, published in BF16. View on Hugging Face
step3 is published by stepfun-ai on Hugging Face, with 37,742 downloads and 166 likes to date. It's a Step3VLForConditionalGeneration model built for image-text-to-text, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 caveat: requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run step3 at its published (BF16) precision: 8× RTX PRO 6000 on runpod, at $1.64/hr per GPU ($13.12/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More stepfun-ai models
- GOT-OCR2_0 (716M, BF16)
- GOT-OCR-2.0-hf (561M, BF16)
- Step-3.5-Flash (199.4B, BF16)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
