DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-mlx_4bit

Description

DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-mlx_4bit is an open-weight text-generation model with roughly 14B parameters published by TheWirelessPhoenix on the Hugging Face Hub. It has 449 downloads. Runs with mlx.

Categories

• Productivity

Tags

• qwen2
• abliterated
• uncensored
• text-generation
• conversational
• 4-bit

Capabilities

• Text generation
• Conversational
• Library: mlx
• 14B parameters