Open-Sora 2.0 (11B) on NVIDIA H200 141GB SXM

Can the NVIDIA H200 141GB SXM run Open-Sora 2.0 (11B)?

Yes, but slowly

Slow. At FP16 it needs about 43.8 GB of 141 GB usable, with an estimated speed of 34.8 min.

Best precision: FP16
Memory mode: Everything on GPU
Time per clip: 34.8 min
Output: 768×768, 129 frames, 50 steps

Download Open-Sora 2.0 (11B)

Original weights · Hugging Face

Full-precision files from HPC-AI Tech, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/hpcai-tech/Open-Sora-v2 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from HPC-AI Tech. The weights themselves download from Hugging Face.

github.com/hpcaitech/Open-Sora (opens in a new tab)

git clone https://github.com/hpcaitech/Open-Sora

Links checked 11 hours ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 70Great quality (A) · 70 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 Slow: How well it runs on the NVIDIA H200 141GB SXM: 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.	31.5 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	4.4 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	7.2 / 15
Match score	68.1 / 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 H200 141GB SXM

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	43.8 GB	141 GB	34.8 min	Everything on GPU	Slow	70Great quality (A) · 70 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

70Great quality (A) · 70 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 RTX PRO 6000 Blackwell FP16 · 36.6 min · Slow
70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 80GB SXM FP16 · 34.8 min · Slow
70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H800 80GB SXM FP16 · 34.8 min · Slow
70Great quality (A) · 70 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 NVL FP16 · 37.8 min · Slow
70Great quality (A) · 70 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 GH200 Grace Hopper (96 GB GPU) FP16 · 34.8 min · Slow
70Great quality (A) · 70 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 RTX PRO 6000 Blackwell Server Edition FP16 · 37.8 min · Slow

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.