ovis image needs about 4.8 GB of memory at F32 (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 0.2 GB (F16) to 7.9 GB (Q8_0).
ovis image is a 7.37B-parameter Ovis model in GGUF format, quantized by convertor. The repository has 7 quant files, from 0.2 GB (F16) to 7.9 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| F32 | 3.1 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_S | 3.3 GB | 4.2 GB | Fits | Get file → | |
| F32 | 3.8 GB | 4.8 GB | Fits | Get file → | |
| IQ4_XS | 4.0 GB | 5.0 GB | Fits | Get file → | |
| IQ4_NL | 4.3 GB | 5.3 GB | Fits | Get file → | |
| Q8_0 | 7.9 GB | 9.4 GB | Too big | Get file → |
What GPU do you need for ovis image?
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 F32 (3.1 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is IQ4_NL (4.3 GB file, about 5.3 GB in use).
- 8 GB VRAM: the best quant that fits is IQ4_NL (4.3 GB file, about 5.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.9 GB file, about 9.4 GB in use).
Which ovis image quant should you choose?
F32 (3.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is F16 at 0.2 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ovis image
How much VRAM does ovis image need?
About 4.8 GB at F32 with an 8K context window. That is the 3.8 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 ovis image on an 8 GB GPU?
Yes, with IQ4_NL: the 4.3 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ovis image GGUF?
It depends on the quant: F16 is 0.2 GB, F32 is 3.1 GB, Q3_K_S is 3.3 GB, F32 is 3.8 GB, IQ4_XS is 4.0 GB, IQ4_NL is 4.3 GB and 1 more.
Where can I download ovis image GGUF?
The files are on Hugging Face in the convertor/ovis-image-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 ovis image 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.