// Open-model VRAM table · family
Wan: local deployment & VRAM
15 open-weight models from Alibaba Wan (26 official repos incl. quantised builds).
official orgs: Wan-AIlatest 2026-08-06memory = estimate
01Video generation (15)
| Model | Params | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|
| Wan2.2-Animate-2-14B-Diffusers | 16.4B | 36.6 GB | 11.4 GB | 16GB GPU | Mac 24GB | Commercial OK | 2026-08-06 |
| Wan2.2-Animate-2-14B-Distilled-Diffusers | 16.4B | 36.6 GB | 11.4 GB | 16GB GPU | Mac 24GB | Commercial OK | 2026-08-06 |
| Wan-Dancer-14B | 14B | 31.3 GB | 9.8 GB | 12GB GPU | Mac 24GB | Commercial OK | 2026-07-10 |
| Wan2.2-Animate-14B-Diffusers ↗ | 17.3B | 38.5 GB | 12.0 GB | 16GB GPU | Mac 24GB | Commercial OK | 2025-11-12 |
| Wan2.2-S2V-14B | 16.3B | 36.4 GB | 11.4 GB | 16GB GPU | Mac 24GB | Commercial OK | 2025-08-25 |
| Wan2.2-I2V-A14B-Diffusers | 14.3B / 14B | 31.9 GB | 10.0 GB | 12GB GPU | Mac 24GB | Commercial OK | 2025-07-28 |
| Wan2.2-T2V-A14B-Diffusers | 14.3B / 14B | 31.9 GB | 10.0 GB | 12GB GPU | Mac 24GB | Commercial OK | 2025-07-28 |
| Wan2.2-TI2V-5B-Diffusers | 5B | 11.5 GB | 3.8 GB | 8GB GPU | Mac 16GB | Commercial OK | 2025-07-28 |
| Wan2.1-VACE-1.3B | 2.15B | 5.2 GB | 1.9 GB | 8GB GPU | Mac 16GB | Commercial OK | 2025-05-13 |
| Wan2.1-VACE-14B | 17.3B | 38.6 GB | 12.1 GB | 16GB GPU | Mac 24GB | Commercial OK | 2025-05-13 |
| Wan2.1-FLF2V-14B-720P | 16.4B | 36.6 GB | 11.4 GB | 16GB GPU | Mac 24GB | Commercial OK | 2025-04-17 |
| Wan2.1-I2V-14B-720P-Diffusers | 16.4B | 36.6 GB | 11.4 GB | 16GB GPU | Mac 24GB | Commercial OK | 2025-03-01 |
| Wan2.1-T2V-1.3B-Diffusers | 1.42B | 3.6 GB | 1.4 GB | 8GB GPU | Mac 16GB | Commercial OK | 2025-03-01 |
| Wan2.1-T2V-14B-Diffusers | 14.3B | 31.9 GB | 10.0 GB | 12GB GPU | Mac 24GB | Commercial OK | 2025-03-01 |
| Wan2.1-I2V-14B-480P | 16.4B | 36.6 GB | 11.4 GB | 16GB GPU | Mac 24GB | Commercial OK | 2025-02-25 |
02Other families
Qwen · IBM Granite · NVIDIA Nemotron · Gemma · Mistral / Magistral / Devstral · GLM / CogVideoX (Z.ai) · DeepSeek · Ai2 OLMo / Molmo · Ant Ling / Ring / Ming · Liquid LFM · MiniCPM / VoxCPM · Tencent Hunyuan / Hy · Phi · Llama · Meituan LongCat · Jina embeddings & rerankers · Kimi · Cohere Command / Aya · Xiaomi MiMo · FLUX · Microsoft VibeVoice / Fara / Harrier · InternLM / Intern-S · StepFun Step · MiniMax · Baidu ERNIE · NVIDIA Parakeet / Canary speech · Stable Diffusion / Stable Audio · Yi (01.AI) · ByteDance Seed · SmolLM / SmolVLM · BGE embeddings & rerankers · LTX Video · FunAudioLLM speech · gpt-oss · poolside Laguna · Whisper · Baichuan · Thinking Machines Inkling · xAI Grok · rednote dots
Totals include 10% + 0.5GB overhead and one 8K-token KV cache for text models. Estimates only. Method →