Gemma 3
Collection
10 items • Updated • 22
gemma-3-27b-it-qat GGUF
Recommended way to run this model:
llama-server -hf ggml-org/gemma-3-27b-it-qat-GGUF -c 0 -fa
Then, access http://localhost:8080
- Downloads last month
- 520
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support