Instructions to use WhiskyAKM/Ling-3.0-Tiny-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 WhiskyAKM/Ling-3.0-Tiny-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 WhiskyAKM/Ling-3.0-Tiny-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf WhiskyAKM/Ling-3.0-Tiny-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 WhiskyAKM/Ling-3.0-Tiny-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf WhiskyAKM/Ling-3.0-Tiny-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 WhiskyAKM/Ling-3.0-Tiny-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf WhiskyAKM/Ling-3.0-Tiny-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 WhiskyAKM/Ling-3.0-Tiny-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf WhiskyAKM/Ling-3.0-Tiny-GGUF:Q4_K_M

Use Docker

docker model run hf.co/WhiskyAKM/Ling-3.0-Tiny-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use WhiskyAKM/Ling-3.0-Tiny-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WhiskyAKM/Ling-3.0-Tiny-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": "WhiskyAKM/Ling-3.0-Tiny-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WhiskyAKM/Ling-3.0-Tiny-GGUF:Q4_K_M

Ollama
How to use WhiskyAKM/Ling-3.0-Tiny-GGUF with Ollama:
```
ollama run hf.co/WhiskyAKM/Ling-3.0-Tiny-GGUF:Q4_K_M
```

Unsloth Studio

How to use WhiskyAKM/Ling-3.0-Tiny-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 WhiskyAKM/Ling-3.0-Tiny-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 WhiskyAKM/Ling-3.0-Tiny-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use WhiskyAKM/Ling-3.0-Tiny-GGUF with Pi:

Start the llama.cpp server

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

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": "WhiskyAKM/Ling-3.0-Tiny-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use WhiskyAKM/Ling-3.0-Tiny-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf WhiskyAKM/Ling-3.0-Tiny-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 "WhiskyAKM/Ling-3.0-Tiny-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"

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

Lemonade

How to use WhiskyAKM/Ling-3.0-Tiny-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull WhiskyAKM/Ling-3.0-Tiny-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ling-3.0-Tiny-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use WhiskyAKM/Ling-3.0-Tiny-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 WhiskyAKM/Ling-3.0-Tiny-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 WhiskyAKM/Ling-3.0-Tiny-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

Ling-3.0-tiny GGUF

GGUF quantized versions of inclusionAI/Ling-3.0-tiny, a lightweight hybrid reasoning MoE model with 7.9B total parameters and 1.3B active parameters per token, supporting English and Chinese, with a 256K context window, tool-calling, and a built-in thinking/reasoning mode.

⚠ Important: Native support for the BailingMoE3 architecture (used by Ling-3.0-tiny) in llama.cpp is currently being developed and has not yet been merged into the main branch. You may need to build llama.cpp from the relevant PR branch (e.g., PR #26608) to use these GGUF files. Until the PR is merged and released, these files will not work with official llama.cpp releases.

Model Overview

Ling-3.0-tiny is a hybrid-linear MoE model built on a native hybrid linear attention architecture, featuring a 3:1 alternating stacking of Kimi Delta Attention (KDA) and Multi-Head Latent Attention (MLA), combined with a sparse MoE FFN comprising 128 routed experts. With 7.9B total parameters and 1.3B activated parameters per token, it balances long-context modeling capability and computational efficiency for local and resource-constrained deployment.

The model uses a Bailing V3-style conversation format with role-based delimiters (<role>SYSTEM</role>, <role>HUMAN</role>, <role>ASSISTANT</role>, <role>OBSERVATION</role>) separated by <|role_end|>. It supports special tokens for thinking/reasoning (controlled via detailed thinking on / detailed thinking off in the system prompt, with reasoning output between think/answer tokens) and tool calling (function blocks with parameter tags).

Model Architecture

Property	Value
Architecture	Hybrid-linear MoE
Total Parameters	7.9B
Activated Parameters	1.3B
Attention Stacking	3 KDA : 1 MLA
Routed Experts	128
Activated Experts	8 + 1 shared
Context Length	262,144 (256K)
Original Precision	bfloat16
Supported Languages	en, zh

Available GGUF Files

File	Quantization	Use Case
`ling-3.0-tiny.gguf`	BF16/FP16	Max precision, reference model
`ling-3.0-tiny-Q8_0.gguf`	Q8_0	Near-lossless, good speed/quality balance
`ling-3.0-tiny-Q6_K.gguf`	Q6_K	Very high quality, recommended for quality
`ling-3.0-tiny-Q5_K_M.gguf`	Q5_K_M	High quality, balanced
`ling-3.0-tiny-Q5_K_S.gguf`	Q5_K_S	High quality, smaller
`ling-3.0-tiny-Q4_K_M.gguf`	Q4_K_M	Good quality, recommended default
`ling-3.0-tiny-Q4_K_S.gguf`	Q4_K_S	Smaller, acceptable quality
`ling-3.0-tiny-Q4_0.gguf`	Q4_0	Legacy quant, fastest inference

Recommended: Q4_K_M or Q5_K_M offer the best quality-to-size trade-off for most use cases.

Usage

llama.cpp CLI

./llama-cli \
  -m ling-3.0-tiny-Q4_K_M.gguf \
  -p "Explain quantum computing in simple terms." \
  --temp 1.0 --top-p 0.95 --top-k 20

llama-server (OpenAI-compatible API)

./llama-server \
  -m ling-3.0-tiny-Q4_K_M.gguf \
  --host 0.0.0.0 --port 8080

Thinking Mode

Thinking mode is enabled by default. The model outputs its reasoning between think and answer tokens before providing the final answer. To control thinking behavior, include detailed thinking on or detailed thinking off in the system prompt. When using an OpenAI-compatible API, you can also pass "chat_template_kwargs": {"enable_thinking": false} to disable thinking per request.

Tool Calling

The model supports function/tool calling. Tool definitions are injected into the system prompt within <tools></tools> XML tags, and the model responds with function blocks containing parameter elements. Tool results are returned via the observation role channel.

Generation Parameters

Recommended parameters from the original model:

Parameter	Value
Temperature	1.0
Top-P	0.95
Top-K	20

Quantization

These GGUF files were created from the BF16 source model using llama-quantize from the llama.cpp project.

Acknowledgements

Original model: inclusionAI/Ling-3.0-tiny
Quantization tool: llama.cpp

License

MIT License

Downloads last month: -

GGUF

Model size

8B params

Architecture

bailingmoe3

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for WhiskyAKM/Ling-3.0-Tiny-GGUF

Base model

inclusionAI/Ling-3.0-tiny

Quantized

(5)

this model