What GPU do I need to run nvidia/Cosmos-H-Surgical?
15.2B parameters, published in BF16. View on Hugging Face
Set up Cosmos-H-SurgicalCosmos-H-Surgical is published by nvidia on Hugging Face, with 10,862 downloads and 22 likes to date. It's a Cosmos3OmniModel model built for image-to-video, published natively in BF16.
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) |
|---|---|---|---|---|---|
| BF16 | 28.3 GB | 33.9 GB | RTX A6000 | 1 | $0.363/hr |
| cheaper alt. | RTX 3060 | 3 | $0.330/hr | ||
| FP8 (quantized) | 14.1 GB | 17.0 GB | RTX 4000 SFF Ada | 1 | $0.198/hr |
| INT4 (quantized) | 7.1 GB | 8.5 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 Cosmos-H-Surgical at its published (BF16) precision: 1× RTX A6000, at $0.363/hr per GPU ($0.363/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Cosmos-H-Surgical: common questions
Can Cosmos-H-Surgical run on a single GPU?
Yes, but not on a desktop card. At BF16 it needs 33.9 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 48.0 GB RTX A6000 at $0.363/hr.
What is the least VRAM Cosmos-H-Surgical can run in?
8.5 GB, at INT4 (quantized), which fits a 12 GB card, against 33.9 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 Cosmos-H-Surgical lower the GPU bill?
Yes. At BF16 the cheapest live fit is one RTX A6000 at $0.363/hr. At INT4 (quantized) it drops to one RTX 3060 at $0.110/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Cosmos models
- Cosmos-Reason2-8B (8.8B, BF16)
- Cosmos-Reason1-7B (8.3B, BF16)
- Cosmos3-Super-Text2Image-4Step (64.0B, BF16)
- Cosmos3-Super-Image2Video (64.6B, BF16)
- Cosmos-Reason2-2B (2.4B, BF16)
Alternatives at this size
Other models for image-to-video within about a third of Cosmos-H-Surgical's 15.2B parameters, from other model lines.
- LTX-2 (18.9B, BF16)
- Wan2.2-I2V-A14B-Diffusers (14.3B, F32)
- lingbot-world-fast (18.5B, F32)
More on Cosmos-H-Surgical
Fits on a 48 GB GPU at BF16: every model that fits in 48 GB.
Fits on a 24 GB GPU at FP8: every model that fits in 24 GB.
Fits on a 12 GB GPU at INT4: every model that fits in 12 GB.
Best video generation models: how Cosmos-H-Surgical ranks against the rest.
Related reading: RTX A6000 pricing and specs, Fast diffusion inference on GPU VMs, and What AI inference is.
