Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-MLX-4bit

Description

Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-MLX-4bit is an open-weight text-generation model with roughly 35B parameters published by nabi-chan on the Hugging Face Hub. It has 201 downloads. Runs with mlx.

Categories

• Research
• Productivity

Tags

• qwen3_5_moe
• mlx-4bit
• quantized
• apple-silicon
• Qwen
• Qwen3.6
• Qwen3_5_moe
• reasoning

Capabilities

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