> Important: This model uses the JANGTQ (JANG TurboQuant) quantization format — an extreme-compression variant of JANG for MLX on Apple Silicon that uses codebook + Hadamard rotation on routed MoE experts while keeping attention, shared expert, dense MLP, embed and lmhead at affine 8-bit. Currently only supported by MLX Studio and the jang-tools` Python package. Follow @dealignai for new releases. Built for vMLX — the only MLX inferencer with VL support, KV cache quantization, prefix cache reuse, agentic tool calling, and speculative decoding. Free for macOS · vmlx.net This is Ling 2.6 Flash by inclusionAI — a 35B-parameter Mixture-of-Experts model with 256 routed experts (8 active per token) + 1 always-active shared expert, hybrid MLA + Lightning Linear-Attention architecture, native English + Chinese, 131K context. It has been: 1. JANGTQ2 quantized — JANGTQ2 profile (8-bit affine on attention, shared expert, dense MLP, embed and lmhead; 2-bit TurboQuant on routed experts with codebook + Hadamard rotation) — 29 GB 2. CRACK abliterated** — permanent weight-level removal of safety refusal JANGTQ2 + CRACK actually edges past the un-cracked MXFP4 base on the same 200 questions. Q2…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: dealignai
Теги: mlx, bailing_hybrid, jang, jangtq, jangtq2, turboquant, quantized, mixed-precision
Лайков: 3 | Загрузок: 159
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
