LocateAnything 3B needs about 2.9 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 2.1 GB (Q4_K_M) to 6.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
LocateAnything 3B – vision‑language grounding model
LocateAnything 3B is a vision‑language model that localizes objects in images based on natural‑language queries. It uses Parallel Box Decoding to predict bounding boxes in a single step, improving speed while maintaining accuracy. The model is trained on 12M images and 138M+ queries across diverse domains.
Good at
- Fast visual grounding
- Dense multi‑object detection
- Point‑based localization
Limits
- No commercial use allowed
- Requires llama.cpp fork with mtmd support
- No vision projector included in this file list
Best for
- Research on visual grounding
- GUI element detection
- Document understanding tasks
Who it’s for. Researchers and developers working on vision‑language grounding who need a fast, high‑quality model for academic or non‑profit projects. The model is not for commercial deployment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q5_K_M | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q6_K | 2.8 GB | 3.6 GB | Fits | Get file → | |
| Q8_0 | 3.6 GB | 4.4 GB | Fits | Get file → | |
| BF16 | 6.8 GB | 7.6 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_K_M (2.11 GB, ~2.9 GB memory at 8k context). If 12 GB VRAM is available, Q5_K_M (2.44 GB, ~3.2 GB memory) offers higher precision. For larger budgets, Q6_K or Q8_0 provide better accuracy at the cost of more memory.
What GPU do you need for LocateAnything 3B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 Q6_K (2.8 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 4.4 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (6.8 GB file, about 7.6 GB in use).
Which LocateAnything 3B quant should you choose?
Q4_K_M is the usual starting point for LocateAnything 3B: it balances file size and quality well. Here it is a 2.1 GB file.
The Q8_0 file is 3.6 GB, about 1.7 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 LocateAnything 3B
How much VRAM does LocateAnything 3B need?
About 2.9 GB at Q4_K_M with an 8K context window. That is the 2.1 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 LocateAnything 3B on an 8 GB GPU?
Yes, with BF16: the 6.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LocateAnything 3B GGUF?
It depends on the quant: Q4_K_M is 2.1 GB, Q5_K_M is 2.4 GB, Q6_K is 2.8 GB, Q8_0 is 3.6 GB, BF16 is 6.8 GB.
What context length does LocateAnything 3B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download LocateAnything 3B GGUF?
The files are on Hugging Face in the yuuko-eth/LocateAnything-3B-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 LocateAnything 3B 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 3B on 8 GB VRAM?
Yes, the Q4_K_M quantized file is 2.11 GB and requires about 2.9 GB memory at 8k context, fitting within 8 GB VRAM.
Does this model support commercial use?
No, the NVIDIA License permits only academic and non‑profit research use; commercial use is not allowed.
What vision projector do I need?
You must pair the LLM quant with the mmproj-LocateAnything-3B-BF16.gguf vision projector to run the model.