What GPU do I need to run nvidia/Cosmos-H-Surgical?
15.2B parameters, published in BF16. View on Hugging Face
Cosmos-H-Surgical is published by nvidia on Hugging Face, with 12,327 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.
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 caveat: 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× A40 on runpod, at $0.440/hr per GPU ($0.440/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More nvidia models
- Gemma-4-31B-IT-NVFP4 (20.9B, BF16)
- parakeet-ctc-1.1b (1.1B, F32)
- nemotron-3.5-asr-streaming-0.6b (638M, F32)
- NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 (31.6B, BF16)
- NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (123.6B, BF16)
- parakeet-tdt-0.6b-v3 (627M, F32)
