What GPU do I need to run microsoft/Phi-3-vision-128k-instruct?
4.1B parameters, published in BF16. View on Hugging Face
Set up Phi-3-vision-128k-instructPhi-3-vision-128k-instruct is published by microsoft on Hugging Face, with 83,905 downloads and 973 likes to date. It's a Phi3VForCausalLM model built for text-generation, published natively in BF16.
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-3-vision-128k-instruct at its published (BF16) precision: 1× RTX 3060 on simplepod, at $0.080/hr per GPU ($0.080/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Phi-3-vision-128k-instruct: common questions
Does Phi-3-vision-128k-instruct fit on a 12 GB GPU?
Yes. At BF16 it needs 9.3 GB of VRAM, so a 12 GB card holds it with 2.7 GB to spare. An 8 GB card is not enough for it at BF16.
What is the least VRAM Phi-3-vision-128k-instruct can run in?
2.3 GB, at INT4 (quantized), which fits a 6 GB card, against 9.3 GB at BF16. 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)
- phi-2 (2.8B, F16)
- VibeVoice-ASR (8.7B, BF16)
- Phi-3.5-vision-instruct (4.1B, BF16)
- Florence-2-large (777M, F16)
- phi-4 (14.7B, BF16)
