---
base_model: microsoft/phi-2
inference: false
language:
- en
license: other
license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
license_name: microsoft-research-license
model_creator: Microsoft
model_name: Phi 2
model_type: phi-msft
pipeline_tag: text-generation
quantized_by: Second State Inc.
tags:
- nlp
- code
---

<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->

# Phi-2-GGUF

## Original Model

[microsoft/phi-2](https://huggingface.co/microsoft/phi-2)

## Run with LlamaEdge

- LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above

- Prompt template

  - Prompt type: `phi-2-instruct`

  - Prompt string

    ```text
    Instruct: <prompt>\nOutput:
    ```

- Context size: `2560`

- Run as LlamaEdge command app

  ```bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:phi-2-Q5_K_M.gguf llama-chat.wasm -p phi-2-instruct
  ```

  **Note that `phi-2` here is only used as an instruct model, instead of a chat model.**

## Quantized GGUF Models

| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [phi-2-Q2_K.gguf](https://huggingface.co/second-state/phi-2-GGUF/blob/main/phi-2-Q2_K.gguf)     | Q2_K   | 2 | 1.11 GB| smallest, significant quality loss - not recommended for most purposes |
| [phi-2-Q3_K_L.gguf](https://huggingface.co/second-state/phi-2-GGUF/blob/main/phi-2-Q3_K_L.gguf) | Q3_K_L | 3 | 1.58 GB| small, substantial quality loss |
| [phi-2-Q3_K_M.gguf](https://huggingface.co/second-state/phi-2-GGUF/blob/main/phi-2-Q3_K_M.gguf) | Q3_K_M | 3 | 1.43 GB| very small, high quality loss |
| [phi-2-Q3_K_S.gguf](https://huggingface.co/second-state/phi-2-GGUF/blob/main/phi-2-Q3_K_S.gguf) | Q3_K_S | 3 | 1.25 GB| very small, high quality loss
| [phi-2-Q4_0.gguf](https://huggingface.co/second-state/phi-2-GGUF/blob/main/phi-2-Q4_0.gguf)     | Q4_0   | 4 | 1.60 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [phi-2-Q4_K_M.gguf](https://huggingface.co/second-state/phi-2-GGUF/blob/main/phi-2-Q4_K_M.gguf) | Q4_K_M | 4 | 1.74 GB| medium, balanced quality - recommended |
| [phi-2-Q4_K_S.gguf](https://huggingface.co/second-state/phi-2-GGUF/blob/main/phi-2-Q4_K_S.gguf) | Q4_K_S | 4 | 1.63 GB| small, greater quality loss |
| [phi-2-Q5_0.gguf](https://huggingface.co/second-state/phi-2-GGUF/blob/main/phi-2-Q5_0.gguf)     | Q5_0   | 5 | 1.93 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [phi-2-Q5_K_M.gguf](https://huggingface.co/second-state/phi-2-GGUF/blob/main/phi-2-Q5_K_M.gguf) | Q5_K_M | 5 | 2.00 GB| large, very low quality loss - recommended |
| [phi-2-Q5_K_S.gguf](https://huggingface.co/second-state/phi-2-GGUF/blob/main/phi-2-Q5_K_S.gguf) | Q5_K_S | 5 | 1.93 GB| large, low quality loss - recommended |
| [phi-2-Q6_K.gguf](https://huggingface.co/second-state/phi-2-GGUF/blob/main/phi-2-Q6_K.gguf)     | Q6_K   | 6 | 2.29 GB| very large, extremely low quality loss |
| [phi-2-Q8_0.gguf](https://huggingface.co/second-state/phi-2-GGUF/blob/main/phi-2-Q8_0.gguf)     | Q8_0   | 8 | 2.96 GB| very large, extremely low quality loss - not recommended |