Instructions to use AtomicChat/Ling-3.1-flash-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-3.1-flash-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-3.1-flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Ling-3.1-flash-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-3.1-flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Ling-3.1-flash-GGUF:Q4_K_M

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 AtomicChat/Ling-3.1-flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf AtomicChat/Ling-3.1-flash-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AtomicChat/Ling-3.1-flash-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use AtomicChat/Ling-3.1-flash-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AtomicChat/Ling-3.1-flash-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-3.1-flash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AtomicChat/Ling-3.1-flash-GGUF:Q4_K_M

Ollama
How to use AtomicChat/Ling-3.1-flash-GGUF with Ollama:
```
ollama run hf.co/AtomicChat/Ling-3.1-flash-GGUF:Q4_K_M
```
Unsloth Desktop

How to use AtomicChat/Ling-3.1-flash-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-3.1-flash-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-3.1-flash-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AtomicChat/Ling-3.1-flash-GGUF with Docker Model Runner:
```
docker model run hf.co/AtomicChat/Ling-3.1-flash-GGUF:Q4_K_M
```

Lemonade

How to use AtomicChat/Ling-3.1-flash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtomicChat/Ling-3.1-flash-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ling-3.1-flash-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use AtomicChat/Ling-3.1-flash-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-3.1-flash-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-3.1-flash-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AtomicChat/Ling-3.1-flash-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-3.1-flash-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-3.1-flash-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"

How to Run Ling 3.1 flash Locally

GGUF builds of inclusionAI's Ling 3.1 flash with our own importance matrix. The calibration corpora behind our builds are public.

Built by the team behind Atomic Chat, the app that runs open-weight models locally and offline.
Runs in llama.cpp build b11571 or newer.

Pick a file

File	Size on disk	KL divergence	top-1
`AD-Q8_0`	600.8 GB	0.00503	97.88%
`AD-Q6_K`	478.0 GB	0.00557	97.72%
`AD-Q5_K_M`	400.2 GB	0.00766	97.34%
`AD-Q4_K_M`	354.4 GB	0.01114	96.86%
`AD-IQ4_XS`	337.8 GB	0.01212	96.64%
`AD-IQ4_XXS`	311.4 GB	0.01391	96.46%
`AD-IQ3_M`	277.1 GB	0.02564	95.27%
`AD-IQ3_XXS`	256.4 GB	0.03436	94.48%
`AD-IQ2_M`	218.1 GB	0.05927	92.72%
`AD-IQ2_XS`	198.2 GB	0.07972	91.64%
`AD-IQ2_XXS`	174.1 GB	0.11133	90.10%
`AD-IQ1_M`	160.9 GB	0.16597	87.86%
`AD-IQ1_S`	141.8 GB	0.20448	86.41%

KL divergence is how far the quantized model's predictions drift from the BF16 model's. Lower is better, and zero means identical. top-1 is how often it picks the same next token the BF16 model would have picked. Both are measured on held-out text; how is at the bottom.

The two 1-bit files are experimental: they matched the BF16 model's token choice 86 to 88% of the time here, so check them on your own tasks first.

AD- marks an Atomic Dynamic layout: the routed experts (97% of the weights) take the low-bit type, while attention, the shared expert, the router and the dense layers stay at q8_0 or higher. The file name is the type of the experts' gate and up projections; their down projections, and all experts of the last five blocks, get a step more.

How much memory it needs

The file has to fit, plus a little for the context. Context is cheap on this model: 63 of its 72 layers use linear attention with a fixed-size state, and only 9 keep a compressed attention cache. That is about 0.5 GB per conversation plus about 10 KB per token.

Total memory (VRAM or unified)	File
192 GB	`AD-IQ1_M`
256 GB	`AD-IQ2_M`
384 GB	`AD-Q4_K_M`
512 GB	`AD-Q5_K_M`
640 GB	`AD-Q8_0`

On a Mac, raise the GPU memory limit first, for example sudo sysctl iogpu.wired_limit_mb=240000 on a 256 GB machine.

Running it

llama-server -hf AtomicChat/Ling-3.1-flash-GGUF:AD-Q4_K_M -ngl 99 -c 32768 --jinja

Each file sits in a folder of its name, split into shards of up to 45 GB; point llama.cpp at the first shard and it loads the rest:

hf download AtomicChat/Ling-3.1-flash-GGUF --include "AD-Q4_K_M/*" --local-dir .
llama-server -m AD-Q4_K_M/Ling-3.1-flash-AD-Q4_K_M-00001-of-00009.gguf -ngl 99 -c 32768 --jinja

The chat template is inside every file. Thinking is on by default. The template switches it with enable_thinking, so a system prompt alone does not turn it off; start the server with

llama-server -hf AtomicChat/Ling-3.1-flash-GGUF:AD-Q4_K_M -ngl 99 -c 32768 --jinja --chat-template-kwargs '{"enable_thinking": false}'

or send "chat_template_kwargs": {"enable_thinking": false} with a request.

How we measured

Reference: BF16 weights converted from inclusionAI's FP8 release and run unquantized (perplexity 2.3590 on the held-out set). Converting FP8 to BF16 rounds each weight once, far below what Q8_0 adds.

Held-out text: eval_neutral from our calibration dataset, never used for calibration, 144 chunks of 4096 tokens. Metric: per-token KL divergence of each file's predictions against the reference, plus top-1 agreement. Hardware: 8x A100-SXM4-80GB, llama.cpp 097cf33d9 for every file.

The importance matrix is the one we computed on 5.5M tokens of the ling3-moe corpus (thinking on and off, tool calls, 30 languages, code, long documents up to 32k tokens), rendered through this model's own chat template.

Model details

Mixture of experts: 512 routed experts in each of 68 layers (the first 4 layers are dense), 8 routed plus 1 shared expert per token, about 24B parameters active of 564B. Hybrid attention: 63 Kimi Delta Attention (linear) layers and 9 multi-head latent attention layers. Hidden size 4096, vocabulary 157,184, context 262,144. The multi-token-prediction head of the release is not included.

Built from inclusionAI's FP8 release (revision b426279f), converted to BF16 and quantized with llama.cpp b11571 (097cf33d9); needs llama.cpp with bailingmoe3 support.

License and credits

MIT, as the original. Base model Ling 3.1 flash by inclusionAI. Quantization and evaluation by AtomicChat.

Downloads last month: 4,038

GGUF

Model size

564B params

Architecture

bailingmoe3

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Model tree for AtomicChat/Ling-3.1-flash-GGUF

Base model

inclusionAI/Ling-3.1-flash

Quantized

(7)

this model

Collection including AtomicChat/Ling-3.1-flash-GGUF

Ling 3.1 Flash

Collection

Atomic Dynamic GGUF quants of inclusionAI Ling 3.1 Flash, measured against the other GGUF builds on one stand. • 4 items • Updated 3 days ago