40

Step 3.5 Flash: Fast Enough to Think. Reliable Enough to Act

Recent model released a couple of weeks ago. "Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token". Beats Kimi K2.5 and GLM 4.7 on more benchmarks than it loses to them.

Edit: there are 4 bit quants that can be run on an 128GB machine like a GB10 [1], AI Max+ 395, or mac studio.

[1] https://forums.developer.nvidia.com/t/running-step-3-5-flash...

5 hours agokristianp

That reverse x axis sure is confusing.

4 hours agowmf

I imagine they thought they'd look better this way. I don't think they do.

an hour agoesafak

Hallucinates like crazy. use with caution. Tested it with a simple "Find me championship decks for X pokemon", "How does Y deck work". Opus 4.6, Deepseek and Kimi all performed well as expected.

2 hours agodanieltanfh95

So who exactly is StepFun? What is their business (how do they make money)? Each time I click “About Stepfun” somewhere on their website, it sends me to a generic landing page in a loop.

2 hours agoSilverElfin

Might want to give it a search.