WA

Wan2.2 I2V A14B

WanGGUF by QuantStackUpdated 2025-07-29
Download on Hugging Face
Parameters14.3B
Context—
Layers—
Architecturewan
Smallest quant5.3 GB
Quick answer

Wan2.2 I2V A14B needs about 11.3 GB of memory at Q4_K_M (a 9.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 5.3 GB (Q2_K) to 15.4 GB (Q8_0).

Wan2.2 I2V A14B – 14.3B parameter image‑to‑video model

Wan2.2 I2V A14B is a 14.3B parameter image‑to‑video model in the Wan family. It uses a Mixture‑of‑Experts architecture and is available in multiple GGUF quantizations. The model is licensed under apache‑2.0 and can be run with llama.cpp.

Good at

  • Image‑to‑video generation
  • Cinematic‑level aesthetics
  • Stable motion synthesis

Limits

  • No vision support beyond image‑to‑video
  • Requires 8k context for estimates
  • Large memory for higher quants

Best for

  • Generating 480P or 720P videos from images
  • Creating stylized video sequences
  • Running on consumer GPUs like 4090

Who it’s for. Developers and researchers needing an open‑source image‑to‑video model with MoE architecture. Suitable for academic projects and industrial applications that require high‑quality video synthesis.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.3 GB 6.4 GB
Fits Get file →
Q2_K5.3 GB 6.4 GB
Fits Get file →
Q3_K_S6.5 GB 7.8 GB
Tight Get file →
Q3_K_S6.5 GB 7.8 GB
Tight Get file →
Q3_K_M7.2 GB 8.5 GB
Too big Get file →
Q3_K_M7.2 GB 8.5 GB
Too big Get file →
Q4_08.6 GB 10.1 GB
Too big Get file →
Q4_K_S8.7 GB 10.3 GB
Too big Get file →
Q4_K_S8.7 GB 10.3 GB
Too big Get file →
Q4_19.3 GB 10.9 GB
Too big Get file →
Q4_K_M9.7 GB 11.3 GB
Too big Get file →
Q4_K_M9.7 GB 11.3 GB
Too big Get file →
Q5_K_S10.1 GB 11.9 GB
Too big Get file →
Q5_K_S10.1 GB 11.9 GB
Too big Get file →
Q5_010.3 GB 12.1 GB
Too big Get file →
Q5_010.3 GB 12.1 GB
Too big Get file →
Q5_K_M10.8 GB 12.6 GB
Too big Get file →
Q5_K_M10.8 GB 12.6 GB
Too big Get file →
Q5_111.0 GB 12.8 GB
Too big Get file →
Q5_111.0 GB 12.8 GB
Too big Get file →
Q6_K12.0 GB 13.9 GB
Too big Get file →
Q6_K12.0 GB 13.9 GB
Too big Get file →
Q8_015.4 GB 17.8 GB
Too big Get file →
Q8_015.4 GB 17.8 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (5.3 GB file, 6.4 GB memory). For 12 GB VRAM, Q3_K_M (7.18 GB file, 8.5 GB memory). For 16 GB VRAM, Q4_K_M (9.65 GB file, 11.3 GB memory).

What GPU do you need for Wan2.2 I2V A14B?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q3_K_S (6.5 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_S (10.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.0 GB file, about 13.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.4 GB file, about 17.8 GB in use).

Which Wan2.2 I2V A14B quant should you choose?

Q4_K_M is the usual starting point for Wan2.2 I2V A14B: it balances file size and quality well. Here it is a 9.7 GB file.

The Q8_0 file is 15.4 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 5.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturewan
Parameters14.3B

Source

Quantized byQuantStack
FamilyWan
Licenseapache-2.0
Downloads (HF)844,918
Last updated2025-07-29

Frequently asked questions about Wan2.2 I2V A14B

How much VRAM does Wan2.2 I2V A14B need?

About 11.3 GB at Q4_K_M with an 8K context window. That is the 9.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Wan2.2 I2V A14B on an 8 GB GPU?

Yes, with Q3_K_S: the 6.5 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Wan2.2 I2V A14B GGUF?

It depends on the quant: Q2_K is 5.3 GB, Q2_K is 5.3 GB, Q3_K_S is 6.5 GB, Q3_K_S is 6.5 GB, Q3_K_M is 7.2 GB, Q3_K_M is 7.2 GB and 18 more.

Where can I download Wan2.2 I2V A14B GGUF?

The files are on Hugging Face in the QuantStack/Wan2.2-I2V-A14B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Wan2.2 I2V A14B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Wan2.2 I2V A14B on 8 GB VRAM?

Use the Q2_K quantization; it requires 6.4 GB memory at 8k context, which fits 8 GB VRAM.

Does the model support text‑to‑video?

No, this model is specifically for image‑to‑video generation.

What license applies to the GGUF files?

The GGUF files retain the original apache‑2.0 license from the parent model.

Other GGUFs of Wan2.2-I2V-A14B

Similar models

Browse all →

More from QuantStack

All by QuantStack →

More Wan models

All Wan →

Other medium models

All medium models →