---
format: "aidr-story-markdown/v1"
id: "b99c151f8719568d862aa90234b92298fcfbce9518c7ccf973e2811062fbe6b9"
canonical_url: "https://aidr.today/b99c151f?lang=en"
title: "Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-18T08:28:04.000Z"
category: "Models"
topics: ["anthropic","claude","multi-agent","open-source"]
source_urls: ["https://prismml.com/news/bonsai-2-27b","https://lobste.rs/s/r9wkkk/bonsai_2_27b_near_lossless_compression_9x"]
summary: "Ternary Bonsai 2 27B retains 98.2% of Qwen3.8 27B benchmark performance in a 5.9GB footprint, with multimodal and agentic capabilities."
---

# Bonsai 2 27B: Near\-Lossless Compression in a 9x Smaller Footprint

> [Open the canonical story](<https://aidr.today/b99c151f?lang=en>)

**Published:** 2026-09-18T08:28:04.000Z
**Category:** Models
**Topics:** anthropic, claude, multi\-agent, open\-source

## Summary

Ternary Bonsai 2 27B retains 98\.2% of Qwen3\.8 27B benchmark performance in a 5\.9GB footprint, with multimodal and agentic capabilities\.

## Sources

- [Story source](<https://prismml.com/news/bonsai-2-27b>)
- [Discussion](<https://lobste.rs/s/r9wkkk/bonsai_2_27b_near_lossless_compression_9x>)