Mistral-Small-3.2-24B-Instruct-2506-GPTQ-AutoRound-TextOnly

Description

Mistral-Small-3.2-24B-Instruct-2506-GPTQ-AutoRound-TextOnly is an open-weight text-generation model with roughly 24B parameters published by ConfidentialMind on the Hugging Face Hub. It has 217 downloads.

Categories

• Productivity

Tags

• mistral
• gptq
• quantization
• 4bit
• confidentialmind
• text-generation
• apache2.0
• mistral-small-24b

Capabilities

• Text generation
• Conversational
• 24B parameters