Instructions to use QDD110/DreamLite-mobile-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use QDD110/DreamLite-mobile-ONNX 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 QDD110/DreamLite-mobile-ONNX
# Run inference directly in the terminal:
llama cli -hf QDD110/DreamLite-mobile-ONNX

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf QDD110/DreamLite-mobile-ONNX
# Run inference directly in the terminal:
llama cli -hf QDD110/DreamLite-mobile-ONNX

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 QDD110/DreamLite-mobile-ONNX
# Run inference directly in the terminal:
./llama-cli -hf QDD110/DreamLite-mobile-ONNX

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 QDD110/DreamLite-mobile-ONNX
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QDD110/DreamLite-mobile-ONNX

Use Docker

docker model run hf.co/QDD110/DreamLite-mobile-ONNX

LM Studio
Jan
Ollama
How to use QDD110/DreamLite-mobile-ONNX with Ollama:
```
ollama run hf.co/QDD110/DreamLite-mobile-ONNX
```

Unsloth Studio

How to use QDD110/DreamLite-mobile-ONNX 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 QDD110/DreamLite-mobile-ONNX 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 QDD110/DreamLite-mobile-ONNX to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QDD110/DreamLite-mobile-ONNX to start chatting

How to use QDD110/DreamLite-mobile-ONNX with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf QDD110/DreamLite-mobile-ONNX

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": "QDD110/DreamLite-mobile-ONNX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use QDD110/DreamLite-mobile-ONNX with Docker Model Runner:
```
docker model run hf.co/QDD110/DreamLite-mobile-ONNX
```

Lemonade

How to use QDD110/DreamLite-mobile-ONNX with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QDD110/DreamLite-mobile-ONNX

Run and chat with the model

lemonade run user.DreamLite-mobile-ONNX-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use QDD110/DreamLite-mobile-ONNX with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf QDD110/DreamLite-mobile-ONNX

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 QDD110/DreamLite-mobile-ONNX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use QDD110/DreamLite-mobile-ONNX with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf QDD110/DreamLite-mobile-ONNX

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 "QDD110/DreamLite-mobile-ONNX" \
  --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"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

DreamLite Mobile ONNX（Pocket Chick 端侧生图引擎套件）

自制 ONNX 导出套件（DMD2 蒸馏 4 步，无 CFG），供 Pocket Chick（小黄鸡）端侧 ONNX Runtime 引擎加载。原始权重（safetensors）来自 carlofkl/DreamLite-mobile。

文件用途

unet_masked.onnx：UNet 主网络（masked 条件，输入 cat([latents, cond], dim=3)）
te_fp16.onnx + te_fp16.onnx.data：文本编码器（ONNX external data）
te_q8.gguf：文本编码器 GGUF 量化版（llama.rn tokenizer + 嵌入）
vae_decoder.onnx / vae_encoder.onnx：VAE 解码/编码（NCHW 输出）

镜像

魔搭镜像：https://www.modelscope.cn/models/zensignGG/DreamLite-mobile-ONNX

采样契约

步数：4（DMD2 蒸馏点）；Guidance Scale 无效（蒸馏进模型）
任务前缀：[Generate]: / [Edit]: ；模板前缀 drop 34 token；max_sequence_length=200
scaling_factor=1.0；mu-shifted flow matching（sigma = linspace(1, 1/steps, steps)）

Downloads last month: -

GGUF

Model size

2B params

Architecture

qwen3vl

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support