Built for vMLX — the MLX inference engine for Apple Silicon with mixed-precision JANG bundles, KV-cache quantization, and agentic tool calling. Free for macOS · vmlx.net The denser 1.75-bit packed variant of Bonsai-2 27B CRACK. Same weights as the ternary Bonsai-2-27B-CRACK-Ternary-JANG, re-packed with the ternarypacked26b codec (26 bytes per 128-weight group carrying 128 base-3 trits, one fp16 scale per group, implicit bias = −scale) — 1.625 bpw codes + 0.125 bpw scale = 1.75 bpw language storage. Vision tower is 6-bit affine as in the ternary bundle, same Hadamard sign encoding, same everything else — this saves ~1.5 GiB of disk vs the ternary shard at bit-for-bit equal decoded weights. Base is prism-ml/Ternary-Bonsai-2-27B-mlx-2bit — PrismML’s ternary compression of the Qwen 3.8 27B qwen35` hybrid (48 GatedDeltaNet SSM + 16 full-attention layers, hidden 5120, separate vision tower, xhigh-default reasoning, XML function calling, 262 K native context). Refusal behavior is removed at the weight level: the model follows instructions across task categories instead of refusing, while keeping its reasoning, coding ability, bilingual knowledge, vision, video and tool-calling intact.…
Модальности:
Генерация текста Компьютерное зрение
Области применения:
Логика и рассуждение Диалог / чат
Задача: Генерация текста
Автор: dealignai
Теги: mlx, qwen3_5, apple-silicon, uncensored, abliterated, crack, jang, ternary
Лайков: 3 | Загрузок: 827
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
