cd/entity/Bonsai 2 27B· home› entities› Bonsai 2 27B
grep -l @bonsai 2 27b /news/*.json | wc -l → 2

Bonsai 2 27B

mentions 2 type Person feed RSS

// recent coverage 2 mentions

22:34
2026-09-17
techcrunch.com
large-language-models

PrismML hopes its tiny LLM will change how we all use AI

PrismML released Bonsai 2 27B on Thursday, a compressed version of Alibaba's Qwen3.8 27B open-source model shrunk to 5.9 GB — a 9x to 10x memory reduction that matches 98% of Qwen's aggregate benchmar…

20:58
2026-09-17
runtimewire.com
large-language-models

PrismML launches a 5.9 GB Qwen3.8 model for local AI

PrismML launched Bonsai 2 27B on September 17th, an Apache 2.0-licensed ternary-weight version of Qwen3.8 27B whose language model fits in 5.95 GB and, according to the company, preserves 98.2% of the…

// co-occurs with top 8 entities
PrismML 2 Qwen3.8 27B 2 Babak Hassibi 2 Khosla Ventures 2 Cerberus 1 Caltech 1 llama.cpp 1 Alibaba 1
// topics top 6 topics
large language models 2 ai products 2 ai research 2 ai startups 2 ai tools 1 machine learning 1