← AI Hashrate 中文

Step

StepFun · 1 models

StepFun's Step-3.5-Flash is a 196.8B MoE at 256K context, Apache-2.0. Beyond retail GPUs; needs multi-GPU or datacenter-class hardware.

Step is the model family from StepFun (阶跃星辰), a Chinese AI lab that has become a community favorite for big open-weight releases. On this site the family currently has one headline member: Step-3.5-Flash, a sparse MoE model released in 2026 under the permissive Apache-2.0 license.

The honest headline up front: this is not a single-GPU hobbyist model. With 196.8B total parameters, even a Q4 quant needs datacenter-class or carefully assembled multi-GPU hardware. The good news is the MoE design — only about 11B parameters are active per token — so once you fit it in VRAM, decode speed feels closer to a 13B-class dense model than a 200B monster.

Size ladder

What makes the Step family special

Which one should you pick

Since the family currently means one model, the real question is whether your hardware tier can hold it:

Links

Models in this family

1 models in the Step family, grouped by series. Q4 (GB) is weights-only; total VRAM adds KV cache and overhead — the fit check links compute it for a representative retail GPU at 8K context.

Step 3.5

ModelParams (B)Ctx (K)Q4 (GB)LicenseFit check
Step-3.5-Flash196.8256108.24apache-2.0on MacBook Pro M3 Max 128GB