Gemma-4 Curated collection of high-performance quantized LLMs optimized for efficient inference, lower VRAM usage, and production deployment. Smartlearners/gemma-4-31B-it-FP8-Dynamic Image-Text-to-Text • 31B • Updated May 18 • 38 Smartlearners/gemma-4-31B-it-INT4-W4A16 Image-Text-to-Text • 32B • Updated May 18 • 6
Gemma-4 Curated collection of high-performance quantized LLMs optimized for efficient inference, lower VRAM usage, and production deployment. Smartlearners/gemma-4-31B-it-FP8-Dynamic Image-Text-to-Text • 31B • Updated May 18 • 38 Smartlearners/gemma-4-31B-it-INT4-W4A16 Image-Text-to-Text • 32B • Updated May 18 • 6
