TechCrunch · Julie Bort ·

PrismML releases Bonsai 2 27B, which compresses Alibaba's Qwen3.8 27B to 5.9 GB, small enough for smartphones, while retaining 98.2% of Qwen's benchmark scores

If AI lab PrismML isn't on your radar yet, it should be

In this story Alibaba Bonsai 2 27B PrismML Qwen3.8-27B

PrismML releases Bonsai 2 27B, which compresses Alibaba's Qwen3.8 27B to 5.9 GB, small enough for smartphones, while retaining 98.2% of Qwen's benchmark scores

Lead Source

TechCrunch — PrismML releases Bonsai 2 27B, which compresses Alibaba's Qwen3.8 27B to 5.9 GB, small enough for smartphones, while retaining 98.2% of Qwen's benchmark scores ↗

How this story grew

Coverage · 0 Discussion · 0

Sep 18Sep 19

More

PrismML News: PrismML News

SiliconANGLE: SiliconANGLE

MarkTechPost: MarkTechPost

RuntimeWire: RuntimeWire

Discussion

Hacker News Lobsters

Martin Matuš Barron Han

@prismml @udiwertheimer @emostaque @vkhosla @0xkydo @xcelestius @babakhassibi

Related stories

Bloomberg: Alibaba releases Qwen3.8-Flash, an open-weight, 125B-parameter model built on its next-gen Qwen 4 architecture, saying it rivals Opus 4.6 and V4-Flash

The Information: Alibaba says its new open-source multimodal model, Qwen3.8-27B, passed 1M+ downloads within a few days of release, making it one of its fastest-growing models

@alibaba_qwen: Alibaba releases weights for Qwen3.8 models under Apache 2.0 license, including Qwen3.8-27B, which it says beats Qwen3.7-Plus and excels in real-world coding

Z.ai: Z.ai releases GLM-5.3-Flash, the first natively multimodal GLM-5 series model, with 320B parameters, and says it served the model as Ox Alpha on Chinese chips

Bloomberg: Tencent releases Hy4 Preview, a 770B-parameter open model with 1M context window, and says it outperforms Z.AI and Moonshot models in internal tests

Discuss with AI

ChatGPT ↗ Claude ↗

← Back to TechSnif