• Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    AI
    Report

    StepFun releases Step 5 Preview, a 600B-parameter open-weights AI model

    NVIDIA says Step 5 Preview runs at nearly 8K tokens per second per GPU on GB300 using NVFP4.

    NVIDIA AINA
    1 Source, 51m ago, first seen 51m ago

    TLDR

    NVIDIA describes Step 5 Preview as StepFun’s largest open-weights release and says the 600B-parameter mixture-of-experts model is built for agent tasks lasting up to 24 hours. StepFun’s model card lists 27B active parameters and a context window of up to 1 million tokens. SGLang provides a deployment guide but says support has not shipped in a standard release; users need its preview Docker image.

    Combined views

    5.3K

    1 Source, first seen 51m ago

    137 likes19 comments13 saves10 reposts

    Combined views

    5.3K

    1 Source, first seen 51m ago

    137 likes19 comments13 saves10 reposts
    Image: @NVIDIAAI on X

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    1 Source

    NVIDIA AI@NVIDIAAICongrats 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/-1h
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    1 Source

    NVIDIA AI@NVIDIAAICongrats 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/-1h
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet