Qwen3.8-Whittle-v40-16.8B

Description

Qwen3.8-Whittle-v40-16.8B is an open-weight text-generation model with roughly 16.8B parameters published by logic65 on the Hugging Face Hub. It has 414 downloads.

Categories

• Productivity

Tags

• pruning
• depth-pruning
• zero-training
• qwen3_5
• gated-deltanet
• text-generation
• conversational

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• 16.8B parameters