Instructions to use AtomicChat/Ling-3.0-flash-VL-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use AtomicChat/Ling-3.0-flash-VL-GGUF 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 AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use AtomicChat/Ling-3.0-flash-VL-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AtomicChat/Ling-3.0-flash-VL-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AtomicChat/Ling-3.0-flash-VL-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M

Ollama
How to use AtomicChat/Ling-3.0-flash-VL-GGUF with Ollama:
```
ollama run hf.co/AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
```
Unsloth Desktop

How to use AtomicChat/Ling-3.0-flash-VL-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M

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": "AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AtomicChat/Ling-3.0-flash-VL-GGUF with Docker Model Runner:
```
docker model run hf.co/AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
```

Lemonade

How to use AtomicChat/Ling-3.0-flash-VL-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ling-3.0-flash-VL-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use AtomicChat/Ling-3.0-flash-VL-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M

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 AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AtomicChat/Ling-3.0-flash-VL-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M

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 "AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M" \
  --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"

Ling-3.0-flash-VL-GGUF / RUNTIME.md

AlexAtomic

Prepare private Ling VL GGUF artifacts and runtime patch

b85d6bb verified 6 days ago

preview code

Raw

History Blame Contribute Delete

1.1 kB

Private CPU runtime

The model requires the accompanying patch; GGUF weights alone do not add support to a stock runtime.

git clone https://github.com/AtomicBot-ai/atomic-llama-cpp-turboquant.git runtime
cd runtime
git checkout cd560939087c95b93a1f30a95603d6b079436952
git apply ../runtime.patch
tar -xzf ../runtime-new-files.tar.gz
cmake -S . -B build -DGGML_CUDA=OFF -DGGML_METAL=OFF -DGGML_NATIVE=ON -DLLAMA_BUILD_SERVER=OFF -DCMAKE_BUILD_TYPE=Release
cmake --build build --target llama-mtmd-cli -j 16

Keep all six files of a variant together. A CPU image example, from the model directory:

runtime/build/bin/llama-mtmd-cli \
  -m Ling-3.0-flash-VL-AD-Q4_K_M-00001-of-00006.gguf \
  --mmproj mmproj-Ling-3.0-flash-VL-F32.gguf \
  --image example.png -p "Describe this image." --jinja -ngl 0

The patch includes model conversion, vision bridge, mRoPE/position handling, and the multi-image CLI batch lifetime fix. The bundled files are source patches, not portable prebuilt binaries. Native compilation requires the usual C++ compiler and CMake build dependencies.