---
format: "aidr-story-markdown/v1"
id: "0902dfba7f5926a5d7743a4943a3494f8531e8260b21b7e3ff0a87d0814147c0"
canonical_url: "https://aidr.today/0902dfba?lang=en"
title: "PrismML Releases Bonsai 2 Local AI Models Starting at 0.43 GB"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-15T20:25:23.000Z"
category: "Open Source"
topics: ["llm","open-source"]
source_urls: ["https://marketbrief.now/ai/prismml-releases-bonsai-2-local-ai-models-starting-at-043-gb-71b9404c","https://huggingnews.com/ai/prismml-releases-bonsai-2-local-ai-models-starting-at-043-gb-71b9404c"]
summary: "PrismML released the Bonsai 2 family of local AI models based on Qwen3.5, ranging from 2B to 27B parameters under the Apache 2.0 license, with the 2B, 4B, and 9B versions featuring weight payloads of 0.43GB, 0.95GB, and 2.0GB respectively."
---

# PrismML Releases Bonsai 2 Local AI Models Starting at 0\.43 GB

> [Open the canonical story](<https://aidr.today/0902dfba?lang=en>)

**Published:** 2026-10-15T20:25:23.000Z
**Category:** Open Source
**Topics:** llm, open\-source

## Summary

PrismML released the Bonsai 2 family of local AI models based on Qwen3\.5, ranging from 2B to 27B parameters under the Apache 2\.0 license, with the 2B, 4B, and 9B versions featuring weight payloads of 0\.43GB, 0\.95GB, and 2\.0GB respectively\.

## Sources

- [Story source](<https://marketbrief.now/ai/prismml-releases-bonsai-2-local-ai-models-starting-at-043-gb-71b9404c>)
- [Story source](<https://huggingnews.com/ai/prismml-releases-bonsai-2-local-ai-models-starting-at-043-gb-71b9404c>)