Ternary Bonsai 2 fits 27B-class multimodal AI into 5.9GB
Ternary Bonsai 2 27B gives local developers a 27B-class multimodal model in a 5.9GB footprint, making deployment on more memory-constrained devices practical. It represents weights with only −1, 0, or +1 plus FP16 scaling, then processes text and images with a 262K-token context window. PrismML reports an aggregate benchmark score of 83.9, retaining 98.2% of its full-precision counterpart’s performance, under Apache 2.0.