[aryonoco]

Gemma 4 31B as hosted by Cerebras is almost too fast! Like I gave it a few different queries and the response was instant and I thought there was something wrong and there was a glitch and I had to double check that I had actually given it the correct prompt.

Mind you Gemma 4 is still Gemma 4, but the speed was really eye opening. Like a glimpse into the future of AI

[mroche]

I'd been hoping for G4 to be added so I could play around with it. Pretty much spent all of last week doing so. I thought something was short-circuiting due to the speed of response, I'd never seen a model operate that fast.

https://inference-docs.cerebras.ai/models/gemma-4-31b