gemma-3-270m-GGUF / README.md
danbev's picture
docs: update command to use llama-cli
360e988 verified
---
base_model:
- google/gemma-3-270m
---
# gemma-3-270m GGUF
Recommended way to run this model:
```sh
llama-cli -hf ggml-org/gemma-3-270m-GGUF -c 0 -fa -p "hello"
```
Then, access http://localhost:8080