Step 5 Preview is StepFun's open-weight MoE for coding, financial research and long-running agents. It has 600B total parameters, 27B active per token and a 1M-token context, with deployment support for vLLM, SGLang and Transformers.
StepFun has released the weights for Step 5 Preview. It was already available via API; now the 600B MoE is on HF. Only 27B parameters are active per token, with a 1M-token context window.
Their technical write-up goes into how they train for long-running agent tasks. They went with 92 transformer layers, sparse attention for the huge context, and even made context compaction part of the RL training, so agents learn what to preserve when they run out of room.
In one test, they gave it 24 hours to optimize an H100 GPU kernel. Its best run reached 508 TFLOPS, compared with 493 for Opus 5 in StepFun's test.
They also let it play Pokémon Red for over 3,000 turns and 6 million tokens. Three Gym Badges, and still only about a third of the way through!
FP8, BF16 and NVFP4 weights are available, with vLLM and SGLang deployment guides.
Can it keep track of earlier decisions when an agent works on a task for several hours?
Support for vLLM, SGLang and Transformers is a nice plus. It gives people more options for trying it out.
How does Step 5 Preview perform on coding tasks compared with other open weight models?
I like that the weights are open. It gives developers more freedom to test the model and run it on their own setup.
Amazing work, cant wait to try it, I wish you also had a RLCD as well for fast decision making, would that be in the works soon as these models would work great if you had a router for reasoning and decision making
About Step 5 Preview on Product Hunt
“600B open weights, trained for long-running agents”
Step 5 Preview launched on Product Hunt on October 17th, 2026 and earned 74 upvotes and 6 comments, placing #15 on the daily leaderboard. Step 5 Preview is StepFun's open-weight MoE for coding, financial research and long-running agents. It has 600B total parameters, 27B active per token and a 1M-token context, with deployment support for vLLM, SGLang and Transformers.
Step 5 Preview was featured in Open Source (68.9k followers) and Artificial Intelligence (481.3k followers) on Product Hunt. Together, these topics include over 146.7k products, making this a competitive space to launch in.
Who hunted Step 5 Preview?
Step 5 Preview was hunted by Zac Zuo. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Step 5 Preview stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Zac Zuo
Hi everyone!
StepFun has released the weights for Step 5 Preview. It was already available via API; now the 600B MoE is on HF. Only 27B parameters are active per token, with a 1M-token context window.
Their technical write-up goes into how they train for long-running agent tasks. They went with 92 transformer layers, sparse attention for the huge context, and even made context compaction part of the RL training, so agents learn what to preserve when they run out of room.
In one test, they gave it 24 hours to optimize an H100 GPU kernel. Its best run reached 508 TFLOPS, compared with 493 for Opus 5 in StepFun's test.
They also let it play Pokémon Red for over 3,000 turns and 6 million tokens. Three Gym Badges, and still only about a third of the way through!
FP8, BF16 and NVFP4 weights are available, with vLLM and SGLang deployment guides.