---
license: apache-2.0
language:
- en
library_name: llama.cpp
pipeline_tag: text-generation
---

# Gemma 2 - Inference Endpoint

## <span style="color: red">NOTICE:</span> This model does, in fact run on inference endpoints. Just click deploy, unlike with regular GGUF models. The model is no longer stored, merely linked. Enjoy <span style="color: red">&lt;3</span>

<label>Code Sample ( One-Shot )</label>
```javascript

{
  "inputs": "A plain old prompt with nothing else"
}
```

## Multi turn coming soon...

Hello! I wrote a simple container that allows for easy running of llama-cpp-python with GGUF models. My goal here was a cheap way to play with Gemma, but then I thought maybe i'd share just in case it's helpful. I'll probably make a bunch of these, so if you have any requests for GGUF or otherwise quantized Llama.cpp models to become inference endpoints, please feel free to reach out!

# Files

I used the excellent quant by [lmstudio-ai/gemma-2b-it-GGUF](https://huggingface.co/lmstudio-ai/gemma-2b-it-GGUF), 

My email is newp@justkidding.net

Just kidding, it's sam att samuellmeyers DOT... com