Video models · Alibaba
Wan 2.1 T2V 14B
- Backbone
- 14.0B
- Native output
- 1280×720, 81 frames
- Default steps
- 50
- License
- apache-2.0
- Released
- 2025-02
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/city96/Wan2.1-T2V-14B-gguf (opens in a new tab)
Original weights · Hugging Face
Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.
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/Wan2.1Memory 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 | 58.0 GB | 46.6 GB | 28.2 GB | Original weights (opens in a new tab) |
FP8 | 38.3 GB | 32.6 GB | 23.3 GB | Original weights (opens in a new tab) |
Q8 GGUF | 39.3 GB | 33.6 GB | 23.6 GB | GGUF (opens in a new tab) |
Q4 GGUF | 32.7 GB | 27.0 GB | 21.3 GB | GGUF (opens in a new tab) |
Components
- Backbone: 14B
- VAE: 0.127B
- umT5-XXL: 5.7B
Best hardware for Wan 2.1 T2V 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.
| Grade · points | Hardware | Precision | Memory | Time per output | Fit |
|---|---|---|---|---|---|
| 79 ptsGreat (A) · 79 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 5.3/15, Memory use 13.9/15 | NVIDIA RTX PRO 6000 Blackwell | FP16 | 58.0 GB / 96.0 GB | 24.4 min | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 3.2/15, Memory use 13.9/15 | AMD Ryzen AI Max+ 395 (128 GB) | FP16 | 58.0 GB / 96.0 GB | 64.0 min | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 1.7/15, Memory use 15.0/15 | Apple M4 Max (64 GB) | Q8 GGUF | 39.3 GB / 48.0 GB | 3.7 h | Runs well |
| 76 ptsGreat (A) · 76 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 1.4/15, Memory use 15.0/15 | Apple M1 Max (64 GB) | Q8 GGUF | 39.3 GB / 48.0 GB | 5.7 h | Runs well |
| 75 ptsGreat (A) · 75 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 1.9/15, Memory use 13.9/15 | Apple M4 Max (128 GB) | FP16 | 58.0 GB / 96.0 GB | 3.3 h | Runs well |
| 74 ptsGreat (A) · 74 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 3.1/15, Memory use 11.6/15 | NVIDIA GB10 (128 GB) | FP16 | 58.0 GB / 115 GB | 69.5 min | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 32.6/45, Memory fit 20.0/25, Speed 4.4/15, Memory use 15.0/15 | NVIDIA GeForce RTX 5090 | Q4 GGUF | 27.0 GB / 32.0 GB | 35.1 min | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 32.6/45, Memory fit 23.0/25, Speed 1.3/15, Memory use 15.0/15 | Apple M4 Pro (48 GB) | Q4 GGUF | 32.7 GB / 36.0 GB | 6.6 h | Tight fit |
| 71 ptsGood (B) · 71 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 2.2/15, Memory use 9.3/15 | Apple M2 Ultra (192 GB) | FP16 | 58.0 GB / 144 GB | 2.4 h | Runs well |
| 69 ptsGood (B) · 69 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 2.2/15, Memory use 7.0/15 | Apple M3 Ultra (256 GB) | FP16 | 58.0 GB / 192 GB | 2.4 h | Runs well |
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.