← Bonsai 27B
What podcasts say about Bonsai 27B
Every statement, with the speaker, the exact quote and the moment it was said.
What experts have said about Bonsai 27B
2 statements · 1 positive · 1 mixed
Prism ML compressed a performant 27-billion-parameter model to approximately six gigabytes.
“they managed to get the model down to ternary, which basically means. Well, I think it was 6 gigabytes for the model. This 27B model, which is really performant.”
Open the episode · Urgent Update- AI Sputnik Moment: Kimi K3 Released w/ Emad Mostaque | Ep. 272Listen at 1:03:40
Ternary quantization reduces Bonsai 27B to six or four gigabytes with accuracy losses.
“With a 5% drop in accuracy, they managed to get it down to 6 gigabytes. And with a 15% drop in accuracy, accuracy down to 4 gigabytes.”
Open the episode · Urgent Update- AI Sputnik Moment: Kimi K3 Released w/ Emad Mostaque | Ep. 272Listen at 1:03:55
Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.