Qwen3.5-4B-MTP-5bit
This repository contains quantized Multi-Token Prediction (MTP) drafter weights split from Qwen/Qwen3.5-4B for use with mlx-vlm speculative decoding....
This repository contains quantized Multi-Token Prediction (MTP) drafter weights split from Qwen/Qwen3.5-4B for use with mlx-vlm speculative decoding....