Wan2.2 Fun 5B Control needs about 4.4 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 13 quants, from 1.9 GB (Q2_K) to 5.4 GB (Q8_0).
Wan2.2 Fun 5B Control – 5 billion‑parameter control model in GGUF format
Wan2.2 Fun 5B Control is a 5 billion‑parameter control model based on the Wan architecture. It is available as a GGUF file and can be used with llama.cpp or ComfyUI. The model is licensed under Apache‑2.0 and supports control‑based generation tasks.
Good at
- Control‑based generation
- Video and image conditioning
- Low‑latency inference with quantization
Limits
- No vision support beyond control inputs
- Requires 8 k context for estimates
- Large memory footprint for high‑quality quants
Best for
- Generating controlled video from reference images
- Creating guided image sequences
- Low‑cost inference on consumer GPUs
Who it’s for. Developers and researchers needing a control‑aware 5 B model for video or image generation. The model is suitable for users with access to GPU hardware and the ability to run llama.cpp or ComfyUI.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.9 GB | 2.6 GB | Fits | Get file → | |
| Q3_K_S | 2.3 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_M | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q4_0 | 3.0 GB | 3.9 GB | Fits | Get file → | |
| Q4_K_S | 3.1 GB | 4.0 GB | Fits | Get file → | |
| Q4_1 | 3.3 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 3.4 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_S | 3.6 GB | 4.5 GB | Fits | Get file → | |
| Q5_0 | 3.7 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_M | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q5_1 | 3.9 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 4.2 GB | 5.2 GB | Fits | Get file → | |
| Q8_0 | 5.4 GB | 6.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 (3.04 GB, ~3.9 GB memory) or Q4_K_S (3.13 GB, ~4 GB). For 12 GB VRAM, Q5_0 (3.65 GB, ~4.6 GB) or Q5_K_M (3.82 GB, ~4.8 GB) provide a balance of quality and memory. Higher quants like Q6_K or Q8_0 require more than 16 GB VRAM.
What GPU do you need for Wan2.2 Fun 5B Control?
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: the best quant that fits is Q4_K_S (3.1 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (4.2 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.4 GB file, about 6.6 GB in use).
Which Wan2.2 Fun 5B Control quant should you choose?
Q4_K_M is the usual starting point for Wan2.2 Fun 5B Control: it balances file size and quality well. Here it is a 3.4 GB file.
The Q8_0 file is 5.4 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 1.9 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
Source
Frequently asked questions about Wan2.2 Fun 5B Control
How much VRAM does Wan2.2 Fun 5B Control need?
About 4.4 GB at Q4_K_M with an 8K context window. That is the 3.4 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 Fun 5B Control on an 8 GB GPU?
Yes, with Q8_0: the 5.4 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Wan2.2 Fun 5B Control GGUF?
It depends on the quant: Q2_K is 1.9 GB, Q3_K_S is 2.3 GB, Q3_K_M is 2.6 GB, Q4_0 is 3.0 GB, Q4_K_S is 3.1 GB, Q4_1 is 3.3 GB and 7 more.
Where can I download Wan2.2 Fun 5B Control GGUF?
The files are on Hugging Face in the QuantStack/Wan2.2-Fun-5B-Control-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 Fun 5B Control 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 Fun 5B Control on 8 GB VRAM?
Yes, with Q4_0 or Q4_K_S quantization the model fits within 8 GB VRAM, using ~3.9–4 GB of GPU memory at 8 k context.
What context length does the model support?
The model estimates memory usage at an 8 k token context. Larger contexts will increase memory requirements proportionally.
Is the model free to use?
The model is released under the Apache‑2.0 license, allowing free use with the original licensing terms retained.