PrismML Releases Bonsai 27B: 1-bit and Ternary Builds of Qwen3.6-27B That Run on Laptops and Phones
” style=”width:100%;border:0;height:600px;display:block;overflow:hidden;” scrolling=”no” loading=”lazy” title=”Bonsai 27B interactive explainer”> That architecture shapes the compression method below. How the Compression Works Each weight is a code, with one shared FP16 scale per group of 128. The effective weight is w_i = s_g · t_i. A ternary value carries log2(3) ≈ 1.585 bits. One FP16 scale per 128…
