gemma-4-31B-it-4bit-NVFP4A16-GPTQ

Description

gemma-4-31B-it-4bit-NVFP4A16-GPTQ is an open-weight text-generation model with roughly 31B parameters published by ebircak on the Hugging Face Hub. It has 684 downloads. Runs with compressed-tensors.

Categories

• Productivity
• Design

Tags

• compressed-tensors
• gemma4
• gemma
• gemma-4
• quantization
• nvfp4
• fp4
• 4bit

Capabilities

• Text generation
• Conversational
• Library: compressed-tensors
• 31B parameters