What GPU do I need to run microsoft/Phi-3.5-vision-instruct?
4.1B parameters, published in BF16. View on Hugging Face
Set up Phi-3.5-vision-instructPhi-3.5-vision-instruct is published by microsoft on Hugging Face, with 681,004 downloads and 738 likes to date. It's a Phi3VForCausalLM model built for image-text-to-text, 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-3.5-vision-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-3.5-vision-instruct: common questions
Does Phi-3.5-vision-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-3.5-vision-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.
Does quantizing Phi-3.5-vision-instruct lower the GPU bill?
Yes. At BF16 the cheapest live fit is one RTX 3060 on simplepod at $0.080/hr. At INT4 (quantized) it drops to one RTX 3070 on simplepod at $0.050/hr, provided a quantized checkpoint exists for 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)
- Florence-2-large (777M, F16)
- phi-4 (14.7B, BF16)
- Phi-3-mini-4k-instruct (3.8B, BF16)
