gpt-oss-120b-TurboQuant-MLX-4bit

Description

gpt-oss-120b-TurboQuant-MLX-4bit is an open-weight text-generation model with roughly 120B parameters published by majentik on the Hugging Face Hub. It has 769 downloads. Runs with mlx.

Categories

• Productivity

Tags

• gpt_oss
• turboquant
• kv-cache-quantization
• gpt-oss
• openai
• moe
• quantized
• 4bit

Capabilities

• Text generation
• Conversational
• Library: mlx
• 120B parameters