Instructions to use dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4",
	filename="model.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 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 dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4
# Run inference directly in the terminal:
llama cli -hf dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4
# Run inference directly in the terminal:
llama cli -hf dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4

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 dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4
# Run inference directly in the terminal:
./llama-cli -hf dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4

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 dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4

Use Docker

docker model run hf.co/dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4

LM Studio
Jan

vLLM

How to use dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4

Ollama
How to use dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 with Ollama:
```
ollama run hf.co/dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4
```

Unsloth Studio

How to use dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 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 dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 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 dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 to start chatting

How to use dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4

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": "dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4

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 dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4

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 "dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4" \
  --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 dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 with Docker Model Runner:
```
docker model run hf.co/dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4
```

Lemonade

How to use dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4

Run and chat with the model

lemonade run user.Qwen2.5-0.5B-Instruct-mobile-int4-{{QUANT_TAG}}

List all available models

lemonade list

Qwen2.5-0.5B-Instruct-mobile-int4 / README.md

3morixd

Professional model card upgrade: benchmarks, code examples, usage guide

904fdbb verified 14 days ago

preview code

Raw

History Blame Contribute Delete

1.09 kB

	---
	language:
	- en
	- zh
	license: apache-2.0
	tags:
	- mobile
	- edge-ai
	- code
	- quantized
	- gguf
	- small-language-model
	pipeline_tag: text-generation
	---

	# Qwen 2.5 0.5B Instruct - Mobile INT4 (GGUF)

	Alibaba's Qwen 2.5 0.5B Instruct, the smallest capable general-purpose model. Incredibly fast on phones.

	\| Property \| Value \|
	\|----------\|-------\|
	\| Base \| Qwen/Qwen2.5-0.5B-Instruct \|
	\| Parameters \| 494 million \|
	\| Quantization \| INT4 GGUF \|
	\| Size \| ~398 MB \|
	\| License \| Apache 2.0 \|

	## Performance

	- ~45 tok/s on Samsung S20 FE CPU (fastest in our collection!)
	- ~0.7 GB memory footprint
	- Fits on ANY modern smartphone
	- ~94% quality retention

	## Use Cases

	- Code generation on mobile IDEs
	- Quick text classification / extraction
	- Embedded assistants in apps
	- Ultra-low-latency responses (<50ms per token)
	- Batch processing at massive scale

	## Quick Start

	```bash
	huggingface-cli download dispatchAI/Qwen2.5-0.5B-Instruct-mobile-int4 --local-dir ./models
	./build/bin/main -m ./models/model.gguf -p "Explain quantum computing simply." -n 128 -t 4
	```