This is an MLX release of an abliterated version of Qwen’s Qwen3.6-35B-A3B. By applying Heretic’s ablation pipeline to the text-side MoE stack, the base refusal behavior was removed at the weight level. This release keeps the Qwen3.6-35B-A3B reasoning and instruction-following profile in Apple MLX format for local deployment on Apple Silicon hardware. This MLX repo includes the retained Qwen3.6 image/video processor files and vision tower tensors for runtimes with Qwen3.6 multimodal MLX support. Qwen3.6-35B-A3B is a sparse MoE model in the qwen35moe family. The accepted abliterated BF16 source checkpoint was produced with a Heretic MPOA/SOMA-style sibling-transfer workflow and finalized with the input-side split-MoE intervention that cleared the official 25-prompt refusal marker suite down to 1/25. This MLX release was built directly from the published BF16 Heretic checkpoint using a high-quality layer-aware quantization policy instead of a flat per-weight pass. — quant target: 6-bit — quant build: 6-bit tuned layer-aware quantization — source checkpoint: Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16 — published variant: Qwen3.6-35B-A3B-Abliterated-Heretic-MLX-6bit The…
Модальности:
Генерация текста Компьютерное зрение Мультимодальность
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Youssofal
Теги: mlx, qwen3_5_moe, mlx-lm, qwen, qwen3.6, moe, mixture-of-experts, multimodal
Лайков: 4 | Загрузок: 381
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
