Instructions to use wardner/LocateAnything-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wardner/LocateAnything-3B with RKLLM:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use wardner/LocateAnything-3B with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wardner/LocateAnything-3B
# Run inference directly in the terminal:
llama cli -hf wardner/LocateAnything-3B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wardner/LocateAnything-3B
# Run inference directly in the terminal:
llama cli -hf wardner/LocateAnything-3B

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf wardner/LocateAnything-3B
# Run inference directly in the terminal:
./build/bin/llama cli -hf wardner/LocateAnything-3B

Use Docker

docker model run hf.co/wardner/LocateAnything-3B

Llama new
LM Studio
Jan
Ollama
How to use wardner/LocateAnything-3B with Ollama:
```
ollama run hf.co/wardner/LocateAnything-3B
```
Unsloth Desktop

How to use wardner/LocateAnything-3B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wardner/LocateAnything-3B

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "wardner/LocateAnything-3B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use wardner/LocateAnything-3B with Docker Model Runner:
```
docker model run hf.co/wardner/LocateAnything-3B
```

Lemonade

How to use wardner/LocateAnything-3B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull wardner/LocateAnything-3B

Run and chat with the model

lemonade run user.LocateAnything-3B-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use wardner/LocateAnything-3B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wardner/LocateAnything-3B

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default wardner/LocateAnything-3B

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use wardner/LocateAnything-3B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wardner/LocateAnything-3B

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "wardner/LocateAnything-3B" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

LocateAnything-3B — [GD]视觉定位模型

English | 简体中文

1. Overview

视觉定位模型，给定文本描述输出图像中目标区域

This repository ships the RK182x deployment artifacts (RKNN graphs + weights) together with the wdnwebui worker manifest (LocateAnything-3b.json).

Item	Value
Model ID	`wardner/LocateAnything-3B`
Display name	LocateAnything-3B
Model type	VLM
Compute target	RK182x
Host platform	RK3588
Runtime	RKLLM + RKNN
Capabilities	`swcap_vision_grounding`
Worker factory	`locate_anything`
Memory estimate	~5500 MB
Init time	~60 s
Cards required	1
Total weight size	3.27 GB

2. Files

Path	Description	Size
`LocateAnything.embed.bin`	fp16 embedding table (vocab × hidden)	596.4 MB
`LocateAnything.tokenizer.gguf`	Tokenizer (GGUF, GPT-2 BPE + ByteLevel)	5.7 MB
`llm_LocateAnything.1828.rknn`	RKNN graph (RK182x compute card, 1.82 TOPS generation)	43.0 MB
`llm_LocateAnything.weight`	Weights paired with the RKNN graph above	1848.4 MB
`vision_LocateAnything.448x448.1828.rknn`	RKNN graph (RK182x compute card, 1.82 TOPS generation)	8.1 MB
`vision_LocateAnything.448x448.weight`	Weights paired with the RKNN graph above	847.5 MB
`LocateAnything-3b.json`	worker manifest — deliberately plain text	793 B

LocateAnything-3b.json is deliberately not in Git LFS. It is the manual of this distribution unit and must stay plain text so it can be diffed, reviewed and previewed on the Hub.

3. Download

hf download wardner/LocateAnything-3B --local-dir ./LocateAnything-3B

Or with git (requires Git LFS):

git clone https://huggingface.co/wardner/LocateAnything-3B

If huggingface.co is unreachable from your network (DNS interception / blocked access), point the client at a mirror instead:

HF_ENDPOINT=https://hf-mirror.com hf download wardner/LocateAnything-3B \
  --local-dir ./LocateAnything-3B

Note: with git clone the weights are Git LFS pointers until git lfs pull completes. hf download fetches the real files directly, and does not create a .git directory — neither is required for the model to work; see §4.

4. Installation (wdnwebui)

Clone the repository into the model root so the folder holds both the weights and the worker manifest:

git clone https://huggingface.co/wardner/LocateAnything-3B /userdata/models/LocateAnything-3B

Then open the web UI → Compute → the card appears under "local compute" (the backend rescans the model root every ~2 s, no restart needed) → click "enable".

The directory name does not have to match the model name: the SDK follows "the folder the manifest was found in", located through the WDNAI_LOCATE_ANYTHING_DIR environment variable declared in the manifest.

5. SHA-256 verification

cd ./LocateAnything-3B
sha256sum -c SHA256SUMS

All entries must report OK before deployment.

6. Caveats and limits

See the notes field of LocateAnything-3b.json — it records the per-model specifics (sampling defaults, capability layout, side effects).

7. License

The upstream model is released under the Apache License 2.0. The files here are RKNN-converted derivatives, not unmodified upstream weights. See LICENSE and NOTICE.

Downloads last month: 53

GGUF

Model size

0 params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support