---
license: other
base_model: nvidia/LocateAnything-3B
base_model_relation: quantized
quantized_by: blockblockblock
library_name: exllamav3
pipeline_tag: text-generation
tags:
- exl3
- exllamav3
- quantized
quantization_format: exl3
bits_per_weight: 6.0
---
# LocateAnything · 3B
EXL3 · 6.0 bpw · 3.9 GB · Dense
[](https://github.com/turboderp-org/exllamav3)
[](#quants)
[](#quants)
[](https://huggingface.co/nvidia/LocateAnything-3B)
[](https://huggingface.co/nvidia/LocateAnything-3B)
[](https://huggingface.co/blockblockblock)
[](https://huggingface.co/collections/blockblockblock/locateanything-3b-exl3-6a205fbdd9aee1d0eba42b33)
---
> [!NOTE]
> An [ExLlamaV3](https://github.com/turboderp-org/exllamav3) build of [`nvidia/LocateAnything-3B`](https://huggingface.co/nvidia/LocateAnything-3B) at **6.0 bits per weight**. See [Quants](#quants) for sibling repos at other bit‑widths or browse the [collection](https://huggingface.co/collections/blockblockblock/locateanything-3b-exl3-6a205fbdd9aee1d0eba42b33).
## Quants
| BPW | Head bits | Calibration rows | Size | Status |
| :---: | :---: | :---: | ---: | :--- |
| 4.0 | 8 | 250 | 3.2 GB | [link](https://huggingface.co/blockblockblock/LocateAnything-3B-exl3-4.0bpw) |
| **6.0** | 8 | 250 | **3.9 GB** | this repo |
## Inference
| Loader |
Use it for |
| TabbyAPI |
OpenAI‑compatible HTTP server. Drop‑in for OpenAI clients. |
| text‑generation‑webui |
Local chat UI. Pick the ExLlamaV3 loader from the model dropdown. |
| ExLlamaV3 |
Direct Python API for embedding the model in your own code or pipeline. |
## Download
```bash
pip install -U huggingface_hub
hf download \
blockblockblock/LocateAnything-3B-exl3-6.0bpw \
--local-dir ./LocateAnything-3B-exl3-6.0bpw
```
Quantization recipe (advanced, embedded in quantization_config.json)
| Setting | Value |
| :--- | :--- |
| Format | `EXL3` |
| Bits per weight | `6.0` |
| Head bits | `8` |
| Calibration rows | `250` |
| Codebook | `MCG` |
| Out‑scales | `always` |
| Parallel mode | `enabled` |
Loaded automatically by every ExLlamaV3 loader; reproduced here for searchability.
## License & use
> [!IMPORTANT]
> Use and license **follow the [base model](https://huggingface.co/nvidia/LocateAnything-3B)**.
> Quantization adds no additional restrictions. Refer to the upstream repository for terms, citation, and safety documentation.
---
Quantized with BlockQuant · convention {org}/{model}-exl3-{bpw}bpw