StarZero All shows Try the podcast clipper →

AI21

2 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement Oct 11, 2025 by Barak Lenz · across every show →

Everything said about AI21, oldest first

Oct 11, 2025 bullish
Assertion Not checkable as stated
Lenz: Local smartphone AI requires hybrid models due to KV cache limits
“So if you wanted to do something local on your phone to search your images, as an example, you can't do that without a hybrid architecture or without doing drastically changes because the model plus KVCache won't fit.”
Barak Lenz Oct 11, 2025 ▶ 13:09 Building Jamba 3B: the tiny Hybrid Transformer State Space Reasoning Model - Barak Lenz, CTO of AI21
Oct 11, 2025
Assertion Partly supported
AI21 CTO: Jamba 3B uses 1:12 attention ratio to cut memory footprint
“So this is a three B dense with only two attentional layers. It's one to 12 and not one to eight, because we wanted to maximize the efficiency. It has very few attention heads, so everything is geared To have, you know, long context with very little memory.”
Barak Lenz Oct 11, 2025 ▶ 15:08 Building Jamba 3B: the tiny Hybrid Transformer State Space Reasoning Model - Barak Lenz, CTO of AI21
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

Try the podcast clipper Learn more