Qwen3.6-35B-A3B-MLX-mixed-4bit

Description

Qwen3.6-35B-A3B-MLX-mixed-4bit is an open-weight text-generation model with roughly 35B parameters published by EigenLabs on the Hugging Face Hub. It has 187 downloads. Runs with mlx.

Categories

• Productivity

Tags

• qwen3_5_moe
• mixed-precision
• apple-silicon
• text-generation
• conversational
• 4-bit

Capabilities

• Text generation
• Conversational
• Library: mlx
• 35B parameters