Wan2.1 needs about 3.0 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.3 GB (Q4_K_M) to 16.8 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Wan2.1 – 9.2B parameter video generation model
Wan2.1 is a 9.2B parameter video foundation model built on the qwen35 architecture. It supports text‑to‑video, image‑to‑video, video editing, text‑to‑image, and video‑to‑audio tasks. The model is available in multiple GGUF quantizations for different VRAM budgets.
Good at
- Text‑to‑Video generation
- Image‑to‑Video conversion
- Video editing and editing tasks
Limits
- No vision support in the base model
- Requires 8.19 GB VRAM for the T2V‑1.3B variant
- License not specified
Best for
- Creating short 480p videos on consumer GPUs
- Rapid prototyping of video generation pipelines
- Academic research with limited GPU resources
Who it’s for. Developers and researchers needing an open, versatile video generation model that runs on consumer‑grade GPUs. It is suitable for teams with limited computing resources who require high‑quality video synthesis.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.3 GB | 3.0 GB | Fits | Get file → | |
| Q8_0 | 0.5 GB | 3.1 GB | Fits | Get file → | |
| F16 | 0.9 GB | 3.6 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 7.7 GB | Tight | Get file → | |
| Q4_K_M | 5.6 GB | 8.3 GB | Too big | Get file → | |
| Q4_K_M | 5.8 GB | 8.5 GB | Too big | Get file → | |
| — | 5.9 GB | 8.6 GB | Too big | Get file → | |
| Q8_0 | 9.8 GB | 12.5 GB | Too big | Get file → | |
| IQ2_M | 10.6 GB | 13.3 GB | Too big | Get file → | |
| IQ3_S | 12.6 GB | 15.3 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_K_M quantization (0.27 GB file, ~3 GB memory at 8k context). For 12 GB VRAM, the Q8_0 quantization (0.45 GB file, ~3.1 GB memory) is a good balance. For larger VRAM budgets, the F16 quant (0.93 GB file, ~3.6 GB memory) offers higher precision.
What GPU do you need for Wan2.1?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: the best quant that fits is F16 (0.9 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (2.7 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (5.0 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (5.9 GB file, about 8.6 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_S (12.6 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (16.8 GB file, about 19.5 GB in use).
Which Wan2.1 quant should you choose?
Q4_K_M is the usual starting point for Wan2.1: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.5 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Wan2.1
How much VRAM does Wan2.1 need?
About 3.0 GB at Q4_K_M with an 8K context window. That is the 0.3 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 Wan2.1 on an 8 GB GPU?
Yes, with Q4_K_M: the 5.0 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Wan2.1 GGUF?
It depends on the quant: Q4_K_M is 0.3 GB, Q8_0 is 0.5 GB, F16 is 0.9 GB, Q4_K_M is 2.7 GB, Q4_K_M is 5.0 GB, Q4_K_M is 5.6 GB and 6 more.
What context length does Wan2.1 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Wan2.1 GGUF?
The files are on Hugging Face in the DeepBeepMeep/Wan2.1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Wan2.1 on an RTX 4090 with 8 GB VRAM?
The T2V‑1.3B variant requires 8.19 GB VRAM, so an RTX 4090 with 8 GB VRAM cannot run it without further optimization.
What quantization should I use for 12 GB VRAM?
Use the Q8_0 quantization (0.45 GB file, ~3.1 GB memory at 8k context) for a good balance of speed and quality.
Does Wan2.1 support Chinese text generation?
Yes, Wan2.1 can generate both Chinese and English text within videos.