Qwen3-30B-A6B-16-Extreme-GGUF

Description

Qwen3-30B-A6B-16-Extreme-GGUF is an open-weight text-generation model with roughly 30B parameters published by Mungert on the Hugging Face Hub. It has 278 downloads. Runs with transformers.

Categories

• Research
• Productivity

Tags

• 32 k context
• reasoning
• thinking
• qwen3
• 16 experts
• text-generation
• conversational

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• Library: transformers
• 30B parameters