StepFun Step 5 Preview demonstrates strong inference performance on NVIDIA GB300
StepFun states that Step 5 Preview demonstrates strong inference performance on NVIDIA GB300 and looks forward to developers building on it. NVIDIA AI, in a quoted tweet, calls this StepFun's largest open-weight release, with a 600B MoE model capable of handling agent tasks up to 24 hours long, reaching nearly 8K tokens/sec/GPU on NVIDIA GB300 with NVFP4, and providing an NVFP4 checkpoint as well as deployment and post-training paths for SGLang, vLLM, NeMo Automodel, and NVIDIA NIM.
Why read this
SelectedAI score 67
StepFun officially confirms the inference performance of Step 5 Preview on NVIDIA GB300, allowing readers to understand its hardware adaptation and deployment path.
Topics
View original postCongrats 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://t.co/poBcZXeWqY Deploy with @SGL_project - https://t.co/2iE8ytEk50 or @vLLM_project - https://t.co/PedItg9OR4 Post-train with NeMo Automodel: https://t.co/KxNt53Sb8k Run it with NVIDIA NIM using a single command: https://t.co/UOWllHNEMW
View original
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://t.co/poBcZXeWqY Deploy with @SGL_project - https://t.co/2iE8ytEk50 or @vLLM_project - https://t.co/PedItg9OR4 Post-train with NeMo Automodel: https://t.co/KxNt53Sb8k Run it with NVIDIA NIM using a single command: https://t.co/UOWllHNEMW
Body
The English body is being prepared. You can open the original source.