baa-ai/Gemma-4-31B-it-RAM-30GB-MLX
9B • Updated • 3.86k • 2
Gemma 4
RAM optimised Gemma 4 models by baa.ai
-
-
baa-ai/Gemma-4-26B-A4B-it-RAM-20GB-MLX
7B • Updated • 1.99k • 4 -
baa-ai/Gemma-4-26B-A4B-it-RAM-14GB-MLX
5B • Updated • 1.76k • 6 -
baa-ai/Gemma-4-26B-A4B-it-RAM-18GB-MLX
6B • Updated • 630 • 1 -
baa-ai/Gemma-4-26B-A4B-it-RAM-22GB-MLX
7B • Updated • 779 • 1 -
baa-ai/Gemma-4-31B-it-RAM-31GB-MLX
Text Generation • 31B • Updated • 1.56k • 1 -
baa-ai/Gemma-4-26B-A4B-it-RAM-8bit-MLX
Image-Text-to-Text • 8B • Updated • 688 • 1 -
baa-ai/Gemma-4-26B-A4B-it-RAM-4bit-MLX
Image-Text-to-Text • 4B • Updated • 691 • 1 -
baa-ai/Gemma-4-31B-it-RAM-8bit-MLX
Image-Text-to-Text • 11B • Updated • 845 • 1 -
baa-ai/Gemma-4-31B-it-RAM-4bit-MLX
Image-Text-to-Text • 6B • Updated • 210 -
baa-ai/Gemma-4-31B-it-RAM-3bit-MLX
Image-Text-to-Text • 5B • Updated • 670 • 1 -
baa-ai/Gemma-4-31B-it-RAM-24GB-MLX
31B • Updated • 170 -
baa-ai/Gemma-4-31B-it-RAM-29GB-MLX
31B • Updated • 265