Instructions to use AtomicChat/Ling-3.0-flash-NVFP4-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-NVFP4-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-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Ling-3.0-flash-NVFP4-GGUF:NVFP4

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-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Ling-3.0-flash-NVFP4-GGUF:NVFP4

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-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf AtomicChat/Ling-3.0-flash-NVFP4-GGUF:NVFP4

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-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AtomicChat/Ling-3.0-flash-NVFP4-GGUF:NVFP4

Use Docker

docker model run hf.co/AtomicChat/Ling-3.0-flash-NVFP4-GGUF:NVFP4

LM Studio
Jan

vLLM

How to use AtomicChat/Ling-3.0-flash-NVFP4-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-NVFP4-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-NVFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AtomicChat/Ling-3.0-flash-NVFP4-GGUF:NVFP4

Ollama
How to use AtomicChat/Ling-3.0-flash-NVFP4-GGUF with Ollama:
```
ollama run hf.co/AtomicChat/Ling-3.0-flash-NVFP4-GGUF:NVFP4
```

Unsloth Studio

How to use AtomicChat/Ling-3.0-flash-NVFP4-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AtomicChat/Ling-3.0-flash-NVFP4-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AtomicChat/Ling-3.0-flash-NVFP4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AtomicChat/Ling-3.0-flash-NVFP4-GGUF to start chatting

How to use AtomicChat/Ling-3.0-flash-NVFP4-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-NVFP4-GGUF:NVFP4

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/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-NVFP4-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use AtomicChat/Ling-3.0-flash-NVFP4-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-NVFP4-GGUF:NVFP4

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-NVFP4-GGUF:NVFP4" \
  --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"

Docker Model Runner
How to use AtomicChat/Ling-3.0-flash-NVFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/AtomicChat/Ling-3.0-flash-NVFP4-GGUF:NVFP4
```

Lemonade

How to use AtomicChat/Ling-3.0-flash-NVFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtomicChat/Ling-3.0-flash-NVFP4-GGUF:NVFP4

Run and chat with the model

lemonade run user.Ling-3.0-flash-NVFP4-GGUF-NVFP4

List all available models

lemonade list

Hermes Agent

How to use AtomicChat/Ling-3.0-flash-NVFP4-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-NVFP4-GGUF:NVFP4

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-NVFP4-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat

Ling-3.0-flash — NVFP4 (GGUF)

inclusionAI/Ling-3.0-flash, 124B total and 5.1B active, with the routed experts in NVFP4: 64 weights packed into 36 bytes as 4-bit E2M1 values with a UE4M3 scale for every 16 of them.

Two builds are published, and the difference between them is the point of this repository.

build	size	mean KLD	99% KLD	top-1 match
`AD-NVFP4`	72.3 GB	0.05363	0.6389	94.86%
`NVFP4_STOCK`	72.3 GB	0.05602	0.6849	94.72%

NVFP4_STOCK is what llama.cpp produces today: the scale of each 16-weight group is amax/6, rounded to nearest, and the importance matrix is discarded. AD-NVFP4 searches the neighbouring UE4M3 scale codes and keeps the one with the smallest importance-weighted error. Same format, same size, same kernels — only the encoder differs, so nothing downstream needs to change.

Requirements

The bailingmoe3 architecture is not in upstream llama.cpp, so these files need a TurboQuant build. Nothing has to be compiled: grab the archive for your machine from release b10269-1.5.0 or newer.

machine	archive
Linux, NVIDIA (CUDA 13)	`llama-turboquant-linux-x64-cuda-13.3.tar.gz`
Linux, NVIDIA (CUDA 12)	`llama-turboquant-linux-x64-cuda-12.4.tar.gz`
DGX Spark / arm64 NVIDIA	`llama-turboquant-linux-arm64-cuda-13.3.tar.gz`
Linux, AMD	`llama-turboquant-linux-x64-rocm.tar.gz`
Linux, any GPU via Vulkan	`llama-turboquant-linux-x64-vulkan.tar.gz`
Linux, CPU only	`llama-turboquant-linux-x64-cpu.tar.gz`
macOS, Apple silicon	`llama-turboquant-macos-arm64.tar.gz`
Windows	`llama-turboquant-windows-x64-cuda-13.3.zip` and friends

wget https://github.com/AtomicBot-ai/atomic-llama-cpp-turboquant/releases/download/b10269-1.5.0/llama-turboquant-linux-x64-cuda-13.3.tar.gz
tar xzf llama-turboquant-linux-x64-cuda-13.3.tar.gz && cd llama-turboquant-*

Intel GPUs are the one gap: there is no SYCL archive, so that path still needs a source build. Stock upstream llama.cpp refuses these files with unknown model architecture: bailingmoe3.

./llama-cli -m AD-NVFP4/Ling-3.0-flash-AD-NVFP4-00001-of-00002.gguf --jinja -ngl 99 -c 32768

Where NVFP4 stands against the rest of the grid

Honest placement, measured on the same held-out text with the same harness:

quant	size	mean KLD	top-1 match
`AD-IQ4_XXS`	69.3 GB	0.03293	96.44%
`AD-Q4_K_S`	74.2 GB	0.03178	96.60%
`AD-NVFP4`	72.3 GB	0.05363	94.86%

A K or IQ quant of the same size is roughly 40% closer to the original. NVFP4 is here for one reason: native FP4 tensor cores on Blackwell (sm_100, sm_120, sm_121). If you are not running Blackwell, take AD-IQ4_XXS instead — it is smaller and more accurate.

We tried four different ways to close that gap by choosing better scales; the best of them bought 4.3%. The remaining distance is structural: the E2M1 value grid is coarse and non-uniform at the top, and the GGUF block format has no per-tensor global scale to compensate. Both are properties of the format, not of the calibration.

Method

Baseline is a bit-exact BF16 conversion of the released weights. The importance matrix was collected on that BF16 model over 522 chunks of 4096 tokens. KL divergence is measured against it on held-out text that never entered the calibration, all runs on the same 4x RTX PRO 6000 Blackwell box. The harness reads 0.00000 when the baseline is measured against itself.

Full grid, logs and json: AtomicChat/Ling-3.0-flash-GGUF and AtomicChat/Ling-3.0-flash-GGUF-metrics.