StepFun releases Step 5 Preview open weights with NVIDIA deployment support

AISummary

NVIDIA AI congratulates StepFun on releasing Step 5 Preview as open weights, its largest open release.

The model is a 600B sparse MoE with 27B active per token, a 1M-token context window and native text and vision input, and BF16 and FP8 weights are on Hugging Face and ModelScope.

NVIDIA says the model runs at nearly 8K tokens/sec/GPU on GB300 using NVFP4, with deployment support through SGLang, vLLM and NVIDIA NIM.

Post on XView on X

NVIDIA AI

@NVIDIAAI

Congrats to StepFun on Step 5 Preview 🙌 Their largest open weights release.

The 600B MoE model is built to handle agent tasks lasting up to 24 hours.

The model runs at nearly 8K tokens/sec/GPU on NVIDIA GB300 using NVFP4.

NVP4 checkpoint: https://huggingface.co/stepfun-ai/Step-5-Preview-NVFP4

Deploy with @SGL_project - https://docs.sglang.io/cookbook/autoregressive/StepFun/Step-5-Preview or @vLLM_project - https://recipes.vllm.ai/stepfun-ai/Step-5-Preview

Post-train with NeMo Automodel: https://github.com/NVIDIA-NeMo/Automodel/blob/main/docs/model-coverage/llm/stepfun-ai/step-5-preview.mdx

Run it with NVIDIA NIM using a single command: https://catalog.ngc.nvidia.com/orgs/nim/nvidia/containers/vllm-model-free-nim-experimental/-

Image from @StepFun_ai's post — StepFun@StepFun_ai

Source: NVIDIA AI · x.comPublished Oct 15, 9:52 AM ET

StepFun releases Step 5 Preview open weights with NVIDIA deployment support

Topics

Tags