Phi Models — Hardware Requirements

5 Phi models from dphn and the community, from the smallest that runs in 0.7 GB of VRAM up to 34.4B parameters. Every row links to full quantization tables and GPU compatibility.

All Phi Models by Size

ModelParamsContext
TinyDolphin 2.8 1.1B1.1B4K
Phi 1 51.4B2K
Phi 11.4B2K
MediPhi Instruct3.8B131K
Dolphin X1 Trinity Nano6.1B131K
Dolphin Mistral 24B Venice Edition24.0B131K
Dolphin 2.9.1 Yi 1.5 34B34.4B8K

Frequently Asked Questions

How much VRAM do I need to run a Phi model?
The smallest Phi model, Phi 1 5, runs from 0.7 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which Phi models can I run on a 16 GB GPU?
7 of 7 Phi models fit in 16 GB of VRAM at some quantization, including Dolphin 2.9.1 Yi 1.5 34B, Phi 1 5, TinyDolphin 2.8 1.1B.
What is the most popular Phi model to run locally?
Dolphin 2.9.1 Yi 1.5 34B is the most downloaded Phi model in local-friendly quantized formats. It runs from 10.3 GB of VRAM.