// Wan · Video generation
Wan2.1-I2V-14B-720P-Diffusers: VRAM & local deployment
16.4B parameters. About 11.4 GB at 4-bit and 36.6 GB at BF16.
released 2025-03-01licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Alibaba Wan · Wan-AI |
|---|---|
| Family / series | Wan · Wan2.1-I2V-720P |
| Type | Video generation (image-to-video) |
| Parameters | 16.4B Source: counted from official safetensors weights |
| Released weights | FP32 · 90.1 GBdownload |
| Licence | Apache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2025-03-01 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Video models: memory grows with resolution and clip length; official repos usually list a tested GPU in the card. Weights below are the main model only.
| Precision | Weights | Weights + overhead | Smallest GPU | Mac |
|---|---|---|---|---|
| BF16 / FP16 (original) | 32.8 GB | 36.6 GB | 2 × RTX 5090 (64GB) | Mac 64GB |
| FP8 / INT8 / Q8_0 | 17.4 GB | 19.7 GB | RTX 4090 24GB | Mac 36GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 9.9 GB | 11.4 GB | 16GB GPU | Mac 24GB |
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- Transformers — mentioned in the official model card
- Diffusers — mentioned in the official model card
- ComfyUI — mentioned in the official model card
04Official repositories & quantised builds
2 official repo(s) from Wan-AI.
- Wan2.1-I2V-14B-720P-Diffusers Diffusers
- Wan2.1-I2V-14B-720P main
05Other Wan models
All 15 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| Wan2.2-Animate-2-14B-Diffusers | 16.4B | 11.4 GB | 2026-08-06 |
| Wan2.2-Animate-2-14B-Distilled-Diffusers | 16.4B | 11.4 GB | 2026-08-06 |
| Wan-Dancer-14B | 14B | 9.8 GB | 2026-07-10 |
| Wan2.2-Animate-14B-Diffusers | 17.3B | 12.0 GB | 2025-11-12 |
| Wan2.2-S2V-14B | 16.3B | 11.4 GB | 2025-08-25 |
| Wan2.2-I2V-A14B-Diffusers | 14.3B / 14B | 10.0 GB | 2025-07-28 |
| Wan2.2-T2V-A14B-Diffusers | 14.3B / 14B | 10.0 GB | 2025-07-28 |
| Wan2.2-TI2V-5B-Diffusers | 5B | 3.8 GB | 2025-07-28 |
06Sources
Data checked 2025-04-04. Parameters, context and licence are copied from the official repository; memory figures are our estimates.