Qwen3.8-27B-MTPLX-Optimized-Speed

Description

Qwen3.8-27B-MTPLX-Optimized-Speed is an open-weight text-generation model with roughly 27B parameters published by Youssofal on the Hugging Face Hub. It has 34,130 downloads. Runs with mlx.

Categories

• Coding
• Productivity

Tags

• qwen3_5
• apple-silicon
• macos
• speculative-decoding
• multi-token-prediction
• qwen
• qwen3.8
• mtp

Capabilities

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