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

Description

Qwen3.8-27B-Abliterated-MTPLX-Optimized-Speed is an open-weight text-generation model with roughly 27B parameters published by PocketAiHub on the Hugging Face Hub. It has 16,089 downloads. Runs with mlx.

Categories

• Coding
• Productivity
• Design

Tags

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

Capabilities

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