Video models ·

Wan 2.1 VACE 14B

Backbone
17.3B
Native output
1280×720, 81 frames
Default steps
50
License
apache-2.0
Released
2025-05

How to run it

Quantized files · GGUF for ComfyUI

Smaller GGUF versions for ComfyUI (with the ComfyUI-GGUF node). No sign-in needed; the model’s license still applies.

huggingface.co/QuantStack/Wan2.1_14B_VACE-GGUF (opens in a new tab)

Original weights · Hugging Face

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

huggingface.co/Wan-AI/Wan2.1-VACE-14B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/Wan-Video/Wan2.1 (opens in a new tab)

git clone https://github.com/Wan-Video/Wan2.1

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

Apps that run Wan 2.1 VACE 14B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

ComfyUI

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

Also good:

Windows PC, NVIDIA GPU

ComfyUI

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

Also good:

Linux, NVIDIA or AMD GPU

ComfyUI

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

Also good:

App Type Opens it as Systems Engine Start
ComfyUI Desktop app Original or GGUF macOSWindowsLinux PyTorch, GGUF via ComfyUI-GGUF Get ComfyUI
SwarmUI Desktop app Original or GGUF macOSWindowsLinux ComfyUI Get SwarmUI
SD.Next Desktop app Original or GGUF macOSWindowsLinux PyTorch Get SD.Next
Stability Matrix Desktop app Original or GGUF macOSWindowsLinux installs ComfyUI, Forge, InvokeAI, SwarmUI, SD.Next or Fooocus Get Stability Matrix
WanGP Desktop app Built-in support WindowsLinux PyTorch Get WanGP

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.

Precision Everything on GPU Text encoder offloaded Sequential offload Download
FP16 64.6 GB 53.2 GB 30.5 GB Original weights (opens in a new tab)
FP8 41.6 GB 35.9 GB 24.4 GB Original weights (opens in a new tab)
Q8 GGUF 42.8 GB 37.1 GB 24.8 GB GGUF (opens in a new tab)
Q4 GGUF 34.7 GB 29.0 GB 22.0 GB GGUF (opens in a new tab)

Components

Best hardware for Wan 2.1 VACE 14B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc Pro B70 (launch price $949) at Q4 GGUF.

Quality Hardware Quant Memory Speed Runs
78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Workstation EditionNVIDIA RTX PRO 6000 Blackwell FP16 64.6 GB / 96.0 GB 26.9 min Slow
72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Founders EditionNVIDIA GeForce RTX 5090 Q4 GGUF 29.0 GB / 32.0 GB 38.6 min Slowtight fit · encoder in RAM
78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GH200 Grace Hopper (96 GB GPU)NVIDIA GH200 Grace Hopper (96 GB GPU) FP16 64.6 GB / 96.0 GB 25.5 min Slow
78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 80GB SXMNVIDIA H100 80GB SXM FP16 64.6 GB / 80.0 GB 25.5 min Slow
78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H800 80GB SXMNVIDIA H800 80GB SXM FP16 64.6 GB / 80.0 GB 25.5 min Slow
78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 NVLNVIDIA H100 NVL FP16 64.6 GB / 94.0 GB 27.7 min Slow
78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Server EditionNVIDIA RTX PRO 6000 Blackwell Server Edition FP16 64.6 GB / 96.0 GB 27.7 min Slow
78Great quality (A) · 78 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. NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition FP16 64.6 GB / 96.0 GB 29.6 min Slow
78Great quality (A) · 78 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. NVIDIA H100 80GB PCIeNVIDIA H100 80GB PCIe FP16 64.6 GB / 80.0 GB 31.2 min Slow
78Great quality (A) · 78 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. NVIDIA A100 80GB PCIeNVIDIA A100 80GB PCIe FP16 64.6 GB / 80.0 GB 38.3 min Slow

Check it on your own hardware

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.

Was this page helpful?