Back to devhandbook.io
Free dev tool

GPU vGPU Split Calculator

One GPU, several VMs. Split it with SR-IOV vGPU — pick your GeForce card and how many VMs want it, and see how much VRAM each gets.

Not listed? Custom:

How this works. NVIDIA's vGPU (SR-IOV) splits a physical GPU into fixed-size profiles, each 1 GB granularity (the "Q" series — 1Q = 1 GB, 8Q = 8 GB, and so on). Each VM gets one virtual function (VF). The combined VRAM of all running vGPUs must fit in physical VRAM, with headroom left for the host driver. Consumer cards are presented as their professional sibling (Ampere → RTX A6000, Ada → RTX 6000 Ada), so the profile table can technically offer sizes larger than your card — we cap to physical VRAM here. This is an estimate: real limits depend on driver version and your host's IOMMU/BAR setup.

vGPU profile reference (VRAM per VM)

Profile VRAM Good for
1Q1 GBTiny models, display only
2Q2 GB~1–3B LLM, light transcoding
4Q4 GB~7B LLM (Q4), small models
8Q8 GB~7B (FP16) / 13B (Q4)
12Q12 GB~13B comfortably
16Q16 GB~20–34B (Q4)
24Q24 GB~34B (FP16) / 70B (Q4)
48Q48 GB~70B (FP16) — datacenter A6000 only