---
license: mit
tags:
- gguf
---
GGUF [llama.cpp](https://github.com/ggerganov/llama.cpp) quantized version of:
- Original model: [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)
- Model creator: [Microsoft](https://huggingface.co/microsoft)
- [License](https://choosealicense.com/licenses/mit/) 

## Recommended Prompt Format (Phi-3)
```
<|system|>
Provide some context and/or instructions to the model.<|end|>
<|user|>
The user’s message goes here<|end|>
<|assistant|>
AI message goes here<|end|>
<|assistant|>
```

Quant Version: [b3405](https://github.com/ggerganov/llama.cpp/releases/tag/b3405) with [imatrix](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)