What GPU do I need to run microsoft/phi-2?
2.8B parameters, published in F16. View on Hugging Face
Set up phi-2phi-2 is published by microsoft on Hugging Face, with 1,481,920 downloads and 3,500 likes to date. It's a PhiForCausalLM model built for text-generation, published natively in F16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run phi-2 at its published (F16) precision: 1× RTX 3070 on simplepod, at $0.050/hr per GPU ($0.050/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
phi-2: common questions
Does phi-2 fit on a 8 GB GPU?
Yes. At FP16 it needs 6.2 GB of VRAM, so an 8 GB card holds it with 1.8 GB to spare. A 6 GB card is not enough for it at FP16.
What is the least VRAM phi-2 can run in?
1.6 GB, at INT4 (quantized), which fits a 6 GB card, against 6.2 GB at FP16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More microsoft models
- Florence-2-base (232M, F16)
- VibeVoice-ASR (8.7B, BF16)
- Phi-3.5-vision-instruct (4.1B, BF16)
- Florence-2-large (777M, F16)
- phi-4 (14.7B, BF16)
- Phi-3-mini-4k-instruct (3.8B, BF16)
