stepfun-ai models

4 stepfun-ai models from StepFun on Hugging Face, from 561M to 321.0B parameters, published by StepFun in BF16, with contexts from 32K to 256K tokens. The smallest official model, GOT-OCR-2.0-hf, needs about 1.3 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.

Pick a size

One row per official stepfun-ai size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
GOT-OCR-2.0-hf561M1.3 GB0.6 GB0.3 GBRTX 3070$0.088/hr3.0 GB
GOT-OCR2_0716M1.6 GB0.8 GB0.4 GBRTX 3070$0.088/hr3.0 GB
Step-3.5-Flash199.4B446 GB223 GB111 GBRTX PRO 6000 × 5$6.88/hrnot published for this architecture
step3321.0B717 GB359 GB179 GBAMD MI300X × 4$10.52/hr122.0 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 (4)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
GOT-OCR-2.0-hf561MBF161.3 GBRTX 3070$0.088/hr
GOT-OCR2_0716MBF161.6 GBRTX 3070$0.088/hr
Step-3.5-Flash199.4BBF16446 GBRTX PRO 6000 × 5$6.88/hr
step3321.0BBF16717 GBAMD MI300X × 4$10.52/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.

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.