PrismML releases Bonsai 2 27B: 5.9 GB Qwen3.8 model, 98% performance
PrismML's Bonsai 2 27B, built on Qwen3.8 27B, is compressed to 5.9 GB via three‑digit quantization, keeping 98.2% performance and adding image processing and tool calling. Open‑source Apache 2.0.
Very good progress for local models.
PrismML released Bonsai 2 27B based on Qwen3.8 27B. After three‑digit quantization the model occupies only 5,9 GB, about nine times smaller than the full version.
According to developer tests it retains 98,2 % of the original performance, while supporting image processing and tool calling. The model under Apache 2.0.
Comments
Weekly digest
The best of vibe coding, AI agents and open source — once a week, no spam.
Related articles
All articlesGLM-5.3 Flash Released: Zhipu's New AI Model Beats GLM-5.2
Zhipu officially releases GLM-5.3 Flash, scoring 84.3 on Terminal-Bench, outperforming GLM-5.2 at 10x lower cost. Open weights, MIT license, 1M context.
Cline Desktop Launches AI Agent Workspace for macOS & Windows
Cline Desktop offers an open‑source AI workspace with parallel agents, task scheduling, checkpoints, branching, and a plugin marketplace, now on macOS and Windows.
Moonshot Releases KIMI K3: The World's Largest Open-Source Model
Moonshot unveils KIMI K3, a 2.8 trillion parameter MoE model with a 1M token context window, outperforming major models in knowledge-based tasks.