shipfeedAI news, curated daily

23:21:03 CET
20 SEPT23:21:03shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

PrismML's Ternary Bonsai 2 27B retains 98.2% performance at 5.9 GB

PrismML releases Ternary Bonsai 2 27B, a ternary-weight model at 5.93 GB that retains 98.2% of its FP16 parent's benchmark performance and runs on a 16 GB laptop.

Sep 18 · · primary fetch1 sourceupdated Sep 18 ·

PrismML released Ternary Bonsai 2 27B, an Apache 2.0 ternary-weight model reported at 5.93 GB versus 53.80 GB in FP16, while retaining 98.2% of the parent model’s average across 20 benchmarks.

The article says it can run on a 16 GB laptop or a single 24 GB GPU with PrismML’s runtime tooling.

read full article on marktechpost.com
§ sources1 publication · timeline below
  1. marktechpost.comPrismML Releases Ternary Bonsai 2 27B: A 5.9 GB Apache 2.0 Model Retaining 98.2% of Qwen3.8 27B Performanceprimary