danbev's picture
docs: remove --jinja option from llama-server command
e7647be verified
---
base_model:
- google/gemma-3-270m-it
---
# gemma-3-270m-it GGUF
Recommended way to run this model:
```sh
llama-server -hf ggml-org/gemma-3-270m-it-GGUF -c 0 -fa
```
Then, access http://localhost:8080