granite-4.1-3b-quantized.w8a8

Description

granite-4.1-3b-quantized.w8a8 is an open-weight text-generation model with roughly 3B parameters published by devpramod-intel on the Hugging Face Hub. It has 1,363 downloads. Runs with transformers.

Categories

• Productivity
• Design

Tags

• granite
• text-generation
• w8a8
• int8
• vllm
• compressed-tensors
• llm-compressor
• conversational

Capabilities

• Text generation
• Conversational
• Library: transformers
• 3B parameters