Mixtral-8x22B-Instruct-v0.1-GGUF

Description

Mixtral-8x22B-Instruct-v0.1-GGUF is an open-weight text-generation model with roughly 22B parameters published by MaziyarPanahi on the Hugging Face Hub. It has 1,274 downloads.

Categories

• Productivity

Tags

• quantized
• 2-bit
• 3-bit
• 4-bit
• 5-bit
• 6-bit
• 8-bit
• 16-bit

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• 22B parameters