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.
cpaua1 min214