Bonsai 27B
Productby PrismML
Heard in 2 episodes across 2 shows since Jul 2026
Bonsai 27B is a high-performance 27-billion-parameter language model developed by PrismML. It utilizes advanced 1-bit and ternary quantization techniques to significantly reduce its memory footprint, making it the first 27B-class model capable of running locally on a smartphone.
Episodes
First heard
Expert statements
Episodes per month
Public PodLume episodes featuring it, over the last year.
Show the data
| Month | Episodes |
|---|---|
| Nov 2025 | 0 |
| Dec 2025 | 0 |
| Jan 2026 | 0 |
| Feb 2026 | 0 |
| Mar 2026 | 0 |
| Apr 2026 | 0 |
| May 2026 | 0 |
| Jun 2026 | 0 |
| Jul 2026 | 1 |
| Aug 2026 | 0 |
| Sep 2026 | 1 |
| Oct 2026 | 0 |
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.
Episodes
2 episodes featuring Bonsai 27B, newest first
