Qwen3.6-27B-4bit-MTP-MLX-Serve

Description

Qwen3.6-27B-4bit-MTP-MLX-Serve is an open-weight text-generation model with roughly 27B parameters published by ddalcu on the Hugging Face Hub. It has 514 downloads. Runs with mlx.

Categories

• Coding
• Productivity

Tags

• qwen3_5
• apple-silicon
• qwen
• qwen3
• mtp
• multi-token-prediction
• speculative-decoding
• mlx-serve

Capabilities

• Text generation
• Conversational
• Library: mlx
• 27B parameters