Phi Models — Hardware Requirements
6 Phi models from Cognitive Computations 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
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| TinyDolphin 2.8 1.1B | 1.1B | 0.8 GB | 4K | ||
| Phi 1 5 | 1.4B | 0.7 GB | 2K | ||
| Phi 1 | 1.4B | 0.7 GB | 2K | ||
| MediPhi Instruct | 3.8B | 2.7 GB | 131K | ||
| Dolphin X1 Trinity Nano | 6.1B | 3.0 GB | 131K | ||
| Dolphin Mistral 24B Venice Edition | 24.0B | 7.3 GB | 131K | ||
| Dolphin Mistral 24B Venice Edition | 24.0B | 10.9 GB | 131K | ||
| Dolphin 2.9.1 Yi 1.5 34B | 34.4B | 10.3 GB | 8K |
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?
- 8 of 8 Phi models fit in 16 GB of VRAM at some quantization, including Dolphin Mistral 24B Venice Edition, Dolphin Mistral 24B Venice Edition, Dolphin 2.9.1 Yi 1.5 34B.
- What is the most popular Phi model to run locally?
- Dolphin Mistral 24B Venice Edition is the most downloaded Phi model in local-friendly quantized formats. It runs from 7.3 GB of VRAM.