What GPU do I need to run stabilityai/stable-virtual-camera?
1.3B parameters, published in F32. View on Hugging FaceGated
Set up stable-virtual-camerastable-virtual-camera is published by stabilityai on Hugging Face, with 10,176 downloads and 237 likes to date. It's a unlisted-architecture model built for image-to-video, published natively in F32, and gated: you'll need to accept the model's terms on Hugging Face before downloading weights.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for activation memory and allocator fragmentation. Diffusion and video models carry no KV-cache. The real driver of extra memory is output resolution and frame count, which this flat overhead does not model. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP32 | 4.7 GB | 5.7 GB | P4 | 1 | $0.069/hr |
| FP8 (quantized) | 1.2 GB | 1.4 GB | RTX 5060 Ti | 1 | $0.160/hr |
| INT4 (quantized) | 0.6 GB | 0.7 GB | RTX 3060 | 1 | $0.110/hr |
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 stable-virtual-camera at its published (F32) precision: 1× P4, at $0.069/hr per GPU ($0.069/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
stable-virtual-camera: common questions
How much VRAM does stable-virtual-camera need?
5.7 GB at FP32, 1.4 GB at FP8 (quantized), 0.7 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 4.7 GB of weights plus inference overhead is the whole requirement.
Do I need approval to download stable-virtual-camera?
Yes. stabilityai gates this repository on Hugging Face, so you have to accept its terms with a signed-in account before the weights will download. It does not change the 5.7 GB the model needs once you have them.
Can stable-virtual-camera run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 4.7 GB, or 5.7 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 2.4 GB, or 2.8 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More stabilityai models
- stable-fast-3d (1.0B, F32)
- stable-audio-3-small-sfx (568M, F32)
Alternatives at this size
Other models for image-to-video within about a third of stable-virtual-camera's 1.3B parameters, from other model lines.
- stable-video-diffusion-img2vid-xt (1.5B, F32)
More on stable-virtual-camera
Fits on an 8 GB GPU at FP32: every model that fits in 8 GB.
Best video generation models: how stable-virtual-camera ranks against the rest.
Related reading: H100 pricing and specs, Fast diffusion inference on GPU VMs, and What AI inference is.
