Model Releases
Today we’re announcing Ternary Bonsai: Top intelligence at 1.58 bits Using ternary weights {-1, 0, +1}, we built a family of models that are…
Today we’re announcing Ternary Bonsai: Top intelligence at 1.58 bits Using ternary weights {-1, 0, +1}, we built a family of models that are 9x smaller than their 16-bit counterparts while outperformi
Today we’re announcing Ternary Bonsai: Top intelligence at 1.58 bits Using ternary weights {-1, 0, +1}, we built a family of models that are 9x smaller than their 16-bit counterparts while outperforming most models in their respective parameter classes on standard benchmarks. We’re open-sourcing the models under the Apache 2.0 license in three sizes: 8B (1.75 GB), 4B (0.86 GB), and 1.7B (0.37 GB).
Related
- Cross-Family Speculative Decoding for Polish Language Models on Apple
Silicon: An Empirical Evaluation of Bielik11B with UAG-Extended MLX-LM - Get more from speculative decoding in MoE models https://cohere.link/Et2rbsB
Source: Emad Mostaque (X) | 2026-04-16