TLDR Tech / AI
Introducing Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint
Ternary Bonsai 2 27B brings stronger reasoning, coding, vision, and agentic capability to the Bonsai series. It uses ternary {−1, 0, +1} weights with FP16 group-wise scaling, for 1.76 effective bits per weight and a total model footprint of 5.9GB. The model supports a 262K-token context window and multimodal text-and-image input. It can be run on Nvidia GPUs via CUDA and on Apple devices via MLX through custom low-bit kernels.
Read the full story