edtorre/ gemma4

1,324 3 months ago

Gemma 4 12B agent-tuned for Hermes Agent and other local agent harnesses. One built for 20GB GPUs the other for 8GB GPUs.

vision tools thinking

2 models

gemma4:12b-agent-20gbGPU
7bfeef5ea067 • 14GB • 256K context window •
Text, Image input • 3 months ago
gemma4:12qat-hermes
dccc988b22a4 • 7.2GB • 256K context window •
Text, Image input • 3 months ago