Wan2.1 Fun 14B InP needs about 12.7 GB of memory at Q4_K_M (a 10.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 6.0 GB (Q2_K) to 32.8 GB (BF16).
Wan2.1 Fun 14B InP – 16.4B parameter GGUF model
Wan2.1 Fun 14B InP is a 16.4B parameter language model in the Wan family. It is available in multiple GGUF quantizations and is licensed under apache-2.0. The model supports 8k context length and can be run with llama.cpp or ComfyUI.
Good at
- Large context handling
- Versatile quantization options
- Compatible with ComfyUI
Limits
- No vision support
- Requires 8k context for full performance
- Large memory footprint for high‑precision quants
Best for
- Local inference on consumer GPUs
- Fine‑tuning with llama.cpp
- Embedding generation for downstream tasks
Who it’s for. Developers and researchers who need a large‑scale language model that can be run locally with various quantization levels. The model is suitable for those who have access to GPUs with at least 12 GB VRAM or can use CPU offload strategies.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 6.0 GB | 7.2 GB | Tight | Get file → | |
| Q3_K_S | 7.4 GB | 8.8 GB | Too big | Get file → | |
| Q3_K_M | 8.1 GB | 9.6 GB | Too big | Get file → | |
| Q4_0 | 9.8 GB | 11.4 GB | Too big | Get file → | |
| Q4_K_S | 10.0 GB | 11.7 GB | Too big | Get file → | |
| Q4_1 | 10.6 GB | 12.4 GB | Too big | Get file → | |
| Q4_K_M | 10.9 GB | 12.7 GB | Too big | Get file → | |
| Q5_K_S | 11.6 GB | 13.5 GB | Too big | Get file → | |
| Q5_0 | 11.8 GB | 13.7 GB | Too big | Get file → | |
| Q5_K_M | 12.3 GB | 14.2 GB | Too big | Get file → | |
| Q5_1 | 12.6 GB | 14.6 GB | Too big | Get file → | |
| Q6_K | 13.8 GB | 15.9 GB | Too big | Get file → | |
| Q8_0 | 17.7 GB | 20.3 GB | Too big | Get file → | |
| BF16 | 32.8 GB | 37.2 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (6.02 GB, 7.2 GB memory). For 12 GB VRAM use Q4_0 (9.77 GB, 11.4 GB memory). For 24 GB VRAM use Q4_K_M (10.86 GB, 12.7 GB memory). Higher quants require more VRAM and disk space.
What GPU do you need for Wan2.1 Fun 14B InP?
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 Q2_K (6.0 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_S (10.0 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (13.8 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (17.7 GB file, about 20.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (17.7 GB file, about 20.3 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (32.8 GB file, about 37.2 GB in use).
Which Wan2.1 Fun 14B InP quant should you choose?
Q4_K_M is the usual starting point for Wan2.1 Fun 14B InP: it balances file size and quality well. Here it is a 10.9 GB file.
The Q8_0 file is 17.7 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 6.0 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 Wan2.1 Fun 14B InP
How much VRAM does Wan2.1 Fun 14B InP need?
About 12.7 GB at Q4_K_M with an 8K context window. That is the 10.9 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 Fun 14B InP on an 8 GB GPU?
Yes, with Q2_K: the 6.0 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Wan2.1 Fun 14B InP GGUF?
It depends on the quant: Q2_K is 6.0 GB, Q3_K_S is 7.4 GB, Q3_K_M is 8.1 GB, Q4_0 is 9.8 GB, Q4_K_S is 10.0 GB, Q4_1 is 10.6 GB and 8 more.
Where can I download Wan2.1 Fun 14B InP GGUF?
The files are on Hugging Face in the city96/Wan2.1-Fun-14B-InP-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 Wan2.1 Fun 14B InP 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 Q4_0 on a 12 GB GPU?
Yes, Q4_0 requires approximately 11.4 GB memory at 8k context, which fits a 12 GB GPU.
What is the disk space needed for Q3_K_S?
The Q3_K_S file is 7.44 GB; you need about 60 GB free disk space for the entire model setup.
Does the model support vision tasks?
No, Wan2.1 Fun 14B InP does not include vision capabilities.