Qwen3-Coder-30B-A3B-Instruct-keep120-Q4_K_M-GGUF

Description

Qwen3-Coder-30B-A3B-Instruct-keep120-Q4_K_M-GGUF is an open-weight text-generation model with roughly 30B parameters published by Joakimpalm-Zen on the Hugging Face Hub. It has 750 downloads.

Categories

• Coding
• Productivity

Tags

• moe
• qwen3moe
• expert-pruning
• structural-derivative
• xyntetik-runner
• text-generation
• conversational

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• 30B parameters