Basic information
Model repository: AMD/gemma-4-12B-it-w4a16-llmcompressor
Organization: AMD
Tasks: text-generation
Architecture and runtime
Model type: gemma4_unified
Architecture: Gemma4UnifiedForConditionalGeneration
Libraries: pytorch, transformer, safetensors
Base models: RedHatAI/gemma-4-12B-it
Current revision: master
License and update history
License: gemma
Created: 2026-09-16
Last updated: 2026-09-20
Hardware requirements
Not filled in locally.
Download links
Not filled in locally.
Basic usage example
Not filled in locally.