Wan22 Bernini 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 8 quants, from 9.7 GB (Q4_K_M) to 15.4 GB (Q8_0).
14.3B parameter Wan model in GGUF format
Wan22 Bernini is a 14.3B parameter model quantized for llama.cpp. It is released under the apache-2.0 license and supports ComfyUI integration. The model is available in several quantization levels.
Good at
- Large language generation
- Fine‑grained text completion
- Contextual understanding
Limits
- No vision support
- Requires at least 8k context
- License is apache-2.0
Best for
- Chatbot back‑ends
- Content drafting
- Code generation
Who it’s for. Developers and researchers who need a large language model that can run on local hardware with llama.cpp. The model is suitable for those who prefer open‑source licensing and ComfyUI compatibility.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 9.7 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_M | 9.7 GB | 11.3 GB | Too big | Get file → | |
| Q5_K_M | 10.8 GB | 12.6 GB | Too big | Get file → | |
| Q5_K_M | 10.8 GB | 12.6 GB | Too big | Get file → | |
| Q6_K | 12.0 GB | 13.9 GB | Too big | Get file → | |
| Q6_K | 12.0 GB | 13.9 GB | Too big | Get file → | |
| Q8_0 | 15.4 GB | 17.8 GB | Too big | Get file → | |
| Q8_0 | 15.4 GB | 17.8 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (9.65 GB file, ~11.3 GB memory at 8k context). For 12 GB VRAM use Q5_K_M (10.79 GB file, ~12.6 GB memory). For 16 GB VRAM use Q6_K (12 GB file, ~13.9 GB memory).
What GPU do you need for Wan22 Bernini?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q4_K_M (9.7 GB file, about 11.3 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 Wan22 Bernini quant should you choose?
Q4_K_M is the usual starting point for Wan22 Bernini: 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Wan22 Bernini
How much VRAM does Wan22 Bernini 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 Wan22 Bernini on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Wan22 Bernini GGUF?
It depends on the quant: Q4_K_M is 9.7 GB, Q4_K_M is 9.7 GB, Q5_K_M is 10.8 GB, Q5_K_M is 10.8 GB, Q6_K is 12.0 GB, Q6_K is 12.0 GB and 2 more.
Where can I download Wan22 Bernini GGUF?
The files are on Hugging Face in the chfm/Wan22_Bernini_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 Wan22 Bernini 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 Wan22 Bernini on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 11.3 GB memory at 8k context.
Does this model support vision tasks?
No, Wan22 Bernini is a text‑only model with no vision capabilities.
What license does the model use?
The model is released under the apache-2.0 license.