Instructions to use VladHong/Ling-3.0-Tiny-APEQ-SubMini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use VladHong/Ling-3.0-Tiny-APEQ-SubMini 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 VladHong/Ling-3.0-Tiny-APEQ-SubMini
# Run inference directly in the terminal:
llama cli -hf VladHong/Ling-3.0-Tiny-APEQ-SubMini

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf VladHong/Ling-3.0-Tiny-APEQ-SubMini
# Run inference directly in the terminal:
llama cli -hf VladHong/Ling-3.0-Tiny-APEQ-SubMini

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 VladHong/Ling-3.0-Tiny-APEQ-SubMini
# Run inference directly in the terminal:
./llama-cli -hf VladHong/Ling-3.0-Tiny-APEQ-SubMini

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 VladHong/Ling-3.0-Tiny-APEQ-SubMini
# Run inference directly in the terminal:
./build/bin/llama-cli -hf VladHong/Ling-3.0-Tiny-APEQ-SubMini

Use Docker

docker model run hf.co/VladHong/Ling-3.0-Tiny-APEQ-SubMini

LM Studio
Jan

vLLM

How to use VladHong/Ling-3.0-Tiny-APEQ-SubMini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VladHong/Ling-3.0-Tiny-APEQ-SubMini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VladHong/Ling-3.0-Tiny-APEQ-SubMini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VladHong/Ling-3.0-Tiny-APEQ-SubMini

Ollama
How to use VladHong/Ling-3.0-Tiny-APEQ-SubMini with Ollama:
```
ollama run hf.co/VladHong/Ling-3.0-Tiny-APEQ-SubMini
```
Unsloth Desktop

How to use VladHong/Ling-3.0-Tiny-APEQ-SubMini with Pi:

Start the llama.cpp server

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

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": "VladHong/Ling-3.0-Tiny-APEQ-SubMini"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use VladHong/Ling-3.0-Tiny-APEQ-SubMini with Docker Model Runner:
```
docker model run hf.co/VladHong/Ling-3.0-Tiny-APEQ-SubMini
```

Lemonade

How to use VladHong/Ling-3.0-Tiny-APEQ-SubMini with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VladHong/Ling-3.0-Tiny-APEQ-SubMini

Run and chat with the model

lemonade run user.Ling-3.0-Tiny-APEQ-SubMini-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use VladHong/Ling-3.0-Tiny-APEQ-SubMini with Hermes Agent:

Start the llama.cpp server

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

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 VladHong/Ling-3.0-Tiny-APEQ-SubMini

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use VladHong/Ling-3.0-Tiny-APEQ-SubMini with OpenClaw:

Start the llama.cpp server

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

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 "VladHong/Ling-3.0-Tiny-APEQ-SubMini" \
  --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-Tiny APEQ SubMini (GGUF)

This repository contains one custom GGUF quantization of inclusionAI/Ling-3.0-tiny, made for local llama.cpp inference where storage and decode speed matter.

It is an APEQ-style, per-tensor mixed-precision profile. It is not a standard uniform Q5_K quantization: the sparse MoE FFN uses Q2_K, most unchanged tensors use Q6_K/Q8_0/F32, and selected later attention tensors use Q5_K.

File

File	Size	SHA-256
`Ling-3.0-Tiny-APEQ-SubMini-3.06GB.gguf`	3,057,430,432 bytes (2.85 GiB)	`5565bad712e9915ba917485a0030d1c4d81765008be27a5b716acb7b4c3e04c1`

The file is 6,897,472 bytes (0.225%) smaller than the local Mini comparator used during this experiment.

Quick start — llama.cpp

Use a recent llama.cpp build with support for the Ling / bailingmoe3 architecture.

llama-cli \
  -m Ling-3.0-Tiny-APEQ-SubMini-3.06GB.gguf \
  -ngl 99 \
  -cnv \
  --reasoning off

To start an OpenAI-compatible local server:

llama-server \
  -m Ling-3.0-Tiny-APEQ-SubMini-3.06GB.gguf \
  -ngl 99 \
  -sm none \
  -c 4096 \
  --reasoning off

The base model's native chat template is embedded in the GGUF. The original model recommends temperature=1.0, top_p=0.95, and top_k=20; use deterministic settings only when reproducing the comparison below.

Validation

This is a local comparative result, not a claim of universal quality equivalence.

The final artifact was regenerated twice from BF16 with the same exact tensor map and had the same SHA-256 each time. On a fresh, disjoint 24-case deterministic ZxBench-derived holdout, it matched the Mini comparator exactly:

Measure	Mini comparator	This GGUF
Holdout mean score	73.292	73.292
Cases scoring >=80	13/24	13/24
Nonterminal/empty results	3	3
V100 decode median	120.658 tok/s	131.810 tok/s
V100 fixed-512 prefill	1,846.080 tok/s	1,723.908 tok/s

Throughput was measured with llama.cpp build b10516 on a Tesla V100-SXM2-16GB, full GPU offload, no speculative decoding, and three samples of a 512-token prefill / 128-token decode workload. Hardware, context length, batching, runtime build, and sampling parameters will affect results.

The holdout used deterministic local graders adapted from ZxBench scenarios. It is a representative comparative screen, not a full hosted ZxBench run with optional AI judges or sandboxes.

Quantization profile

Tensor type	Count
F32	215
Q2_K	72
Q5_K	62
Q6_K	102
Q8_0	75

The profile preserves higher precision in the early sensitive attention path and lowers standard attention tensors in blocks 5–23, plus blk.4.attn_q.weight, to Q5_K. Broader reductions were screened and rejected due to measurable regressions.

License and attribution

This quantization is derived from inclusionAI/Ling-3.0-tiny and follows its MIT license. Please review the upstream model card for the original model's capabilities, limitations, and usage guidance.

Downloads last month: -

GGUF

Model size

8B params

Architecture

bailingmoe3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for VladHong/Ling-3.0-Tiny-APEQ-SubMini

Base model

inclusionAI/Ling-3.0-tiny

Quantized

(25)

this model