IP Adapter needs about 0.8 GB of memory at Q5_1 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.
IP Adapter is a 349M-parameter Adapter model in GGUF format, quantized by Solictous. The repository has 1 quant file, from 0.3 GB (Q5_1) to 0.3 GB (Q5_1).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_1 | 0.3 GB | 0.8 GB | Fits | Get file → |
What GPU do you need for IP Adapter?
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 Q5_1 (0.3 GB file, about 0.8 GB in use).
Which IP Adapter quant should you choose?
Q5_1 (0.3 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about IP Adapter
How much VRAM does IP Adapter need?
About 0.8 GB at Q5_1 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 IP Adapter on an 8 GB GPU?
Yes, with Q5_1: the 0.3 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of IP Adapter GGUF?
It depends on the quant: Q5_1 is 0.3 GB.
Where can I download IP Adapter GGUF?
The files are on Hugging Face in the Solictous/IP-Adapter-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 IP Adapter 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.