Model reference · open weights
step3 is an open-weight language model from stepfun-ai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Introduction Step3 is our cutting-edge multimodal reasoning model—built on a Mixture-of-Experts architecture with 321B total parameters and 38B active. It is designed end-to-end to minimize decoding costs while delivering top-tier performance in vision–language reasoning. Through the co-design of Multi-Matrix Factorization Attention (MFA) and Attention-FFN Disaggregation (AFD), Step3 maintains exceptional efficiency across both flagship and low-end accelerators. Step3 model card: Evaluation Results Deployment [!Note] Step3's API is accessible at https://platform.stepfun.com/, where we offer OpenAI-compatible API for you. Inference with Hugging Face Transformers We introduce how to use our model at inference stage using transformers library. It is recommended to use python=3.10, torch=2.1.0, and transformers=4.54.0 as the development environment.We currently only support bf16 inference, and multi-patch for image preprocessing is supported by default. This behavior is aligned with vllm and sglang. Inference with vLLM and SGLang Our model checkpoints are stored in bf16 and block-fp8 format, you can find it on Huggingface. Currently, it is recommended to run Step3 on the following inference engines: vLLM SGLang Deployment and Request examples for vLLM and SGLang can be found in the Model Deployment Guide. Contact Us If you have any questions, please reach out at contact@stepfun.com . License Both the code repository and the model weights are released under the Apache License (Version 2.0). Citation
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | stepfun-ai |
|---|---|
| Type | Language models |
| Parameters (lead) | 321.0B |
| Variants | 1 |
| Runs with | transformers |
| Released | 2025-07-28 |
| Popularity | 39k downloads / month |
| Likes | 166 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| step3 | 321.0B | BF16 | ~738.2 GB | — | Weights ↗ |
Using it via the API
Once AxForge deploys step3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (step3 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"step3","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗