What GPU do I need to run stepfun-ai/Step-3.5-Flash?
199.4B parameters, published in BF16. View on Hugging Face
Set up Step-3.5-FlashStep-3.5-Flash is published by stepfun-ai on Hugging Face, with 155,341 downloads and 833 likes to date. It's a Step3p5ForCausalLM model built for text-generation, 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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 371.4 GB | 445.7 GB | A100 | 6 | $7.27/hr |
| FP8 (quantized) | 185.7 GB | 222.8 GB | RTX 4080 Super | 7 | $2.37/hr |
| INT4 (quantized) | 92.8 GB | 111.4 GB | RTX A5000 | 5 | $0.880/hr |
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 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Step-3.5-Flash at its published (BF16) precision: 6× A100, at $1.21/hr per GPU ($7.27/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Step-3.5-Flash: common questions
Can Step-3.5-Flash run on a single GPU?
No. At BF16 it needs 445.7 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 80.0 GB A100, and it takes 6 of them.
How many GPUs do I need to run Step-3.5-Flash?
6 at BF16. It needs 445.7 GB of VRAM and the cheapest capable live offer is a 80.0 GB A100, so 6 of them come to $7.27/hr in total.
Does quantizing Step-3.5-Flash lower the GPU bill?
Yes. At BF16 the cheapest live fit is 6 A100 cards at $7.27/hr. At INT4 (quantized) it drops to 5 RTX A5000 cards at $0.880/hr, provided a quantized checkpoint exists for it.
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)
- step3 (321.0B, BF16)
- bert-base-uncased (110M, F32)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
Related reading: A100 pricing and specs, and The best GPUs for AI, ranked.
