---
pipeline_tag: text-generation
tags:
- exllama
- exl2
- phi
- code
- math
- tchat
- text-generation
---

**Quantization**: ExLlamaV2 (ExL2) at **2.5 bits** per weight.

## Overview
This is an ExLlamaV2 (ExL2) 2.5 bpw quantized version of [microsoft/phi-4](https://huggingface.co/microsoft/phi-4).

## Quantization By
I often have idle A100 GPUs while building/testing the app, so I put them to use quantizing models.

I hope the community finds these quantizations useful.

Andrew Webby @ [RolePlai](https://roleplai.app/)