Cosmos3-Super Image2Video (64B) on NVIDIA RTX PRO 6000 Blackwell

Can the NVIDIA RTX PRO 6000 Blackwell run Cosmos3-Super Image2Video (64B)?

Yes, but slowly (CPU offload)

Slow (CPU offload). At FP16 it needs about 53.7 GB of 96.0 GB usable, with an estimated speed of 35.7 min.

Best precision: FP16
Memory mode: Sequential CPU offload
Time per clip: 35.7 min
Output: 832×480, 189 frames, 50 steps

Best app to run it on the NVIDIA RTX PRO 6000 Blackwell

On Windows

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

On Linux

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Cosmos3-Super Image2Video (64B)

Original weights · Hugging Face

Full-precision files from NVIDIA, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/nvidia/Cosmos3-Super-Image2Video (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from NVIDIA. The weights themselves download from Hugging Face.

github.com/nvidia/cosmos (opens in a new tab)

git clone https://github.com/nvidia/cosmos

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at FP16, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs SlowCPU offload: How well it runs on the NVIDIA RTX PRO 6000 Blackwell: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	39.6 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	12.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	4.3 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	12.9 / 15
Match score	68.8 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every precision on the NVIDIA RTX PRO 6000 Blackwell

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	53.7 GB	96.0 GB	35.7 min	Sequential CPU offload	SlowCPU offload	88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA B200 FP16 · 22.8 min · Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI300X FP16 · 33.7 min · Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI325X FP16 · 33.7 min · Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip FP16 · 38.4 min · Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI350X FP16 · 38.5 min · Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 80GB SXM FP16 · 34.0 min · Slow (CPU offload)

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.