Florence 2 base needs about 0.7 GB of memory at Q4_K (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.
Florence‑2 base – a prompt‑based vision foundation model
Florence‑2 base is a vision foundation model from Microsoft. It uses a prompt‑based approach to perform tasks such as captioning, object detection, and segmentation. The model is available in GGUF format with a Q4_K quantization.
Good at
- Captioning
- Object detection
- Segmentation
Limits
- No vision‑language tasks beyond vision
- Requires 8k context for full functionality
- MIT license only
Best for
- Image captioning in low‑resource settings
- Quick object detection demos
- Segmentation tasks with limited GPU memory
Who it’s for. Developers and researchers needing a lightweight vision model for inference on modest hardware. The model is suitable for prototyping and educational purposes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.1 GB | 0.7 GB | Fits | Get file → |
The Q4_K quantized file is 0.14 GB and requires approximately 0.7 GB of VRAM at 8k context. This makes it suitable for GPUs with 4 GB or more of VRAM. For tighter budgets, consider using a lower‑precision quantization if available.
What GPU do you need for Florence 2 base?
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 (0.1 GB file, about 0.7 GB in use).
Which Florence 2 base quant should you choose?
Q4_K (0.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Florence 2 base
How much VRAM does Florence 2 base need?
About 0.7 GB at Q4_K with an 8K context window. That is the 0.1 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 Florence 2 base on an 8 GB GPU?
Yes, with Q4_K: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Florence 2 base GGUF?
It depends on the quant: Q4_K is 0.1 GB.
Where can I download Florence 2 base GGUF?
The files are on Hugging Face in the antflydb/Florence-2-base repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Florence 2 base use?
Hugging Face lists the license as mit. 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 Florence‑2 base on a GPU with 8 GB VRAM?
Yes, the Q4_K quantized model requires about 0.7 GB of VRAM at 8k context, well within an 8 GB GPU.
Does Florence‑2 base support vision‑language tasks?
No, this base model is limited to vision tasks and does not support vision‑language capabilities.