locate anything.cpp needs about 6.7 GB of memory at Q6_K (a 5.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 4.7 GB (Q4_K) to 9.2 GB (F16).
LocateAnything 3B vision‑language grounding model
LocateAnything 3B is a 3.83 billion‑parameter vision‑language model designed for fast, high‑quality visual grounding. It supports object localization, dense detection, and point‑based localization across diverse domains. The model is released for research and non‑commercial use only.
Good at
- Fast visual grounding
- Dense multi‑object detection
- Point‑based localization
Limits
- No commercial use
- No vision support beyond grounding
- Requires NVIDIA license
Best for
- Research on visual grounding
- Academic projects needing fast detection
- Non‑commercial prototype development
Who it’s for. Researchers and developers working on vision‑language tasks who need a fast, open‑source grounding model. The model is suitable for academic and non‑profit projects and must be used under NVIDIA’s non‑commercial license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 4.7 GB | 5.8 GB | Fits | Get file → | |
| Q5_K | 5.1 GB | 6.2 GB | Fits | Get file → | |
| Q6_K | 5.5 GB | 6.7 GB | Fits | Get file → | |
| Q8_0 | 6.3 GB | 7.5 GB | Tight | Get file → | |
| F16 | 9.2 GB | 10.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K (4.72 GB file, ~5.8 GB memory). For 12 GB VRAM, Q5_K (5.1 GB file, ~6.2 GB memory) or Q6_K (5.51 GB file, ~6.7 GB memory). For 16 GB VRAM, Q8_0 (6.26 GB file, ~7.5 GB memory) offers higher precision.
What GPU do you need for locate anything.cpp?
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: the best quant that fits is Q4_K (4.7 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (6.3 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (9.2 GB file, about 10.8 GB in use).
Which locate anything.cpp quant should you choose?
Q6_K (5.5 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q4_K at 4.7 GB, with the quality trade-offs that come with fewer bits. 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 locate anything.cpp
How much VRAM does locate anything.cpp need?
About 6.7 GB at Q6_K with an 8K context window. That is the 5.5 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 locate anything.cpp on an 8 GB GPU?
Yes, with Q8_0: the 6.3 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of locate anything.cpp GGUF?
It depends on the quant: Q4_K is 4.7 GB, Q5_K is 5.1 GB, Q6_K is 5.5 GB, Q8_0 is 6.3 GB, F16 is 9.2 GB.
Where can I download locate anything.cpp GGUF?
The files are on Hugging Face in the mudler/locate-anything.cpp-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 locate anything.cpp use?
Hugging Face lists the license as other. 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 LocateAnything on 8 GB VRAM?
Yes, the Q4_K quantization requires about 5.8 GB of VRAM at 8 k context, which fits within 8 GB.
Is commercial use allowed?
No. The NVIDIA license permits only academic and non‑profit research use.
Does the model support vision tasks beyond grounding?
No. It is focused solely on visual grounding and does not provide general vision capabilities.