Model reference · open weights
Step-3.5-Flash 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
Step 3.5 Flash [](https://github.com/stepfun-ai/Step-3.5-Flash) [](https://huggingface.co/stepfun-ai/Step-3.5-Flash) [](https://modelscope.cn/models/stepfun-ai/Step-3.5-Flash) [](https://discord.gg/RcMJhNVAQc) [](https://static.stepfun.com/blog/step-3.5-flash/) [](https://arxiv.org/abs/2602.10604) []() [](https://openrouter.ai/chat?models=stepfun/step-3.5-flash:free) [](https://huggingface.co/spaces/stepfun-ai/Step-3.5-Flash) 1. Introduction Step 3.5 Flash (visit website) is our most capable open-source foundation model, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. This "intelligence density" allows it to rival the reasoning depth of top-tier proprietary models, while maintaining the agility required for real-time interaction. 2. Key Capabilities - Deep Reasoning at Speed: While chatbots are built for reading, agents must reason fast. Powered by 3-way Multi-Token Prediction (MTP-3), Step 3.5 Flash achieves a generation throughput of 100–300 tok/s in typical usage (peaking at 350 tok/s for single-stream coding tasks). This allows for complex, multi-step reasoning chains with immediate responsiveness. - A Robust Engine for Coding & Agents: Step 3.5 Flash is purpose-built for agentic tasks, integrating a scalable RL framework that drives consistent self-improvement. It achieves 74.4% on SWE-bench Verified and 51.0% on Terminal-Bench 2.0, proving its ability to handle sophisticated, long-horizon tasks with unwavering stability. - Efficient Long Context: The model supports a cost-efficient 256K context window by employing a 3:1 Sliding Window Attention (SWA) ratio—integrating three SWA layers for every full-attention layer. This hybrid approach ensures consistent performance across massive datasets or long codebases while significantly reducing the computational overhead typical of standard long-context models. - Accessible Local Deployment: Optimized for accessibility, Step 3.5 Flash brings elite-level intelligence to local environments. It runs securely on high-end consumer hardware (e.g., Mac
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | stepfun-ai |
|---|---|
| Type | Language models |
| Parameters (lead) | 199.4B |
| Context | 256k tokens |
| Variants | 3 |
| Runs with | transformers |
| Based on | stepfun-ai/step-3.5-flash |
| Released | 2026-02-01 |
| Popularity | 155k downloads / month |
| Likes | 833 |
| 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.
Using it via the API
Once AxForge deploys step-3-5-flash for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (step-3-5-flash 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":"step-3-5-flash","messages":[{"role":"user","content":"Hello"}]}'
Details
Tags
Papers
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗