SkyReels V2 T2V 14B 540P on NVIDIA H100 80GB SXM

Can the NVIDIA H100 80GB SXM run SkyReels V2 T2V 14B 540P?

Yes, but slowly

Slow. At FP16 it needs about 49.0 GB of 80.0 GB usable and takes about 16.3 min per clip.

Best precision: FP16
Memory mode: Everything on GPU
Time per clip: 16.3 min
Output: 960×544, 97 frames, 50 steps

Best app to run it on the NVIDIA H100 80GB SXM

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

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

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 SkyReels V2 T2V 14B 540P

Original weights · Hugging Face

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

huggingface.co/Skywork/SkyReels-V2-T2V-14B-540P (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/SkyworkAI/SkyReels-V2 (opens in a new tab)

git clone https://github.com/SkyworkAI/SkyReels-V2

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (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 H100 80GB 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.	33.3 / 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.	6.4 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	14.1 / 15
Match score	78.9 / 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 H100 80GB SXM

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	49.0 GB	80.0 GB	16.3 min	Everything on GPU	Slow	74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	29.3 GB	80.0 GB	14.6 min	Everything on GPU	Slow	72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP8 · 17.6 min · Slow (tight fit)
74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP16 · 17.1 min · Slow
74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 FP16 · 30.3 min · Slow (CPU offload)
74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX FP16 · 33.8 min · Slow (CPU offload)
72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT FP8 · 36.2 min · Slow (tight fit · CPU offload)
72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 FP8 · 36.4 min · Slow (tight fit · CPU offload)

Quick answers

How much memory does SkyReels V2 T2V 14B 540P need on the NVIDIA H100 80GB SXM?

At FP16 it needs about 49.0 GB. The NVIDIA H100 80GB SXM has 80.0 GB usable.

How long does SkyReels V2 T2V 14B 540P take on the NVIDIA H100 80GB SXM?

About 16.3 min per clip at FP16 and default settings, an estimate scaled from a reference timing by this hardware’s compute speed.

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.