This repository contains Multi-Token Prediction (MTP) drafter weights split from Qwen/Qwen3.6-27B for use with mlx-vlm speculative decoding. This is not a standalone chat or text-generation model. Load it as the draft model alongside a compatible Qwen3.6 27B target checkpoint. — Model type: qwen35mtp — MTP block size: 2 — Target architecture: Qwen3.6 27B — Precision: bf16 — Runtime: MLX / mlx-vlm — Format: Safetensors with MLX-compatible config and tokenizer files The stored tensors are unquantized MLX-compatible drafter weights. Use this repo only as a speculative decoding drafter for compatible Qwen3.6 27B checkpoints. The target model verifies drafted tokens, while this MTP model proposes candidate tokens per decoding step. This checkpoint requires runtime support for Qwen/DeepSeek MTP draft models in mlx-vlm. Standard standalone generation through generic Transformers APIs is not expected to work with this repository by itself. Please refer to the upstream Qwen/Qwen3.6-27B model card and license terms for model usage constraints.
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: mlx-community
Теги: mlx, qwen3_5_mtp, mlx-vlm, qwen3.6, qwen3.6-27b, qwen, mtp, speculative-decoding
Лайков: 3 | Загрузок: 108
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
