# Hugging Face (Twitter)RT @HuggingPapers: StepFun's Step 3.5 FlashA sparse MoE model with 196B parameters, 11B active ...

**Published:** February 12, 2026
**Author:** t.me
**Source:** Hugging Face (KB)
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/hugging-face-twitter-rt-huggingpapers-stepfun-s-step-3-5-flasha-sparse-m

Hugging Face (Twitter)RT @HuggingPapers: StepFun's Step 3.5 FlashA sparse MoE model with 196B parameters, 11B active ....

> From the original source: **Hugging Face (KB)**
> [Read full article at Hugging Face (KB)](https://t.me/huggingface/2302)

**Tags:** #Google DeepMind #OpenAI #Hugging Face

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*