SkyReels V2 T2V 14B 540P on NVIDIA GeForce RTX 4070 SUPER

Can the NVIDIA GeForce RTX 4070 SUPER run SkyReels V2 T2V 14B 540P?

9 pts

No, it doesn’t fit

No. SkyReels V2 T2V 14B 540P needs about 14.2 GB even at FP8; the NVIDIA GeForce RTX 4070 SUPER has 12.0 GB usable.

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 7 days ago against Hugging Face, Ollama and GitHub.

How the F grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	9.8 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	0.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	0.0 / 15
Total	9.8 / 100	9 ptsWon't run (F) · 9 of 100 points: Model quality 9.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every precision on the NVIDIA GeForce RTX 4070 SUPER

Precision	Memory needed	Available	Time per output	Memory mode	Fit	Grade · points	Download
`FP16`	19.1 GB	12.0 GB	—	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 10.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Original weights (opens in a new tab)
`FP8`	14.2 GB	12.0 GB	—	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 9.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Original weights (opens in a new tab)

Hardware that can run it

76 ptsGreat (A) · 76 of 100 points: Model quality 32.6/45, Memory fit 23.0/25, Speed 6.2/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 FP8 · 17.6 min
76 ptsGreat (A) · 76 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 6.3/15, Memory use 11.8/15 NVIDIA RTX PRO 6000 Blackwell FP16 · 17.1 min
74 ptsGreat (A) · 74 of 100 points: Model quality 32.6/45, Memory fit 25.0/25, Speed 1.8/15, Memory use 15.0/15 Apple M4 Pro (48 GB) FP8 · 3.4 h
74 ptsGreat (A) · 74 of 100 points: Model quality 32.6/45, Memory fit 25.0/25, Speed 2.3/15, Memory use 14.1/15 Apple M4 Max (64 GB) FP8 · 2.1 h
73 ptsGreat (A) · 73 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 3.9/15, Memory use 11.8/15 AMD Ryzen AI Max+ 395 (128 GB) FP16 · 44.8 min
73 ptsGreat (A) · 73 of 100 points: Model quality 32.6/45, Memory fit 25.0/25, Speed 1.9/15, Memory use 14.1/15 Apple M1 Max (64 GB) FP8 · 3.1 h

Models that do run on the NVIDIA GeForce RTX 4070 SUPER

75 ptsGreat (A) · 75 of 100 points: Model quality 22.1/45, Memory fit 23.0/25, Speed 15.0/15, Memory use 15.0/15 LTX-Video 2B FP8 · 42 s
72 ptsGreat (A) · 72 of 100 points: Model quality 19.8/45, Memory fit 23.0/25, Speed 15.0/15, Memory use 15.0/15 CogVideoX 2B FP8 · 1.7 min
70 ptsGood (B) · 70 of 100 points: Model quality 24.3/45, Memory fit 20.0/25, Speed 11.2/15, Memory use 15.0/15 CogVideoX 5B FP8 · 5.3 min
70 ptsGood (B) · 70 of 100 points: Model quality 24.3/45, Memory fit 20.0/25, Speed 11.2/15, Memory use 15.0/15 CogVideoX 5B I2V FP8 · 5.3 min
68 ptsGood (B) · 68 of 100 points: Model quality 24.8/45, Memory fit 20.0/25, Speed 8.9/15, Memory use 15.0/15 Wan 2.1 VACE 1.3B FP16 · 8.6 min

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.