Instructions to use dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile", dtype="auto")

llama-cpp-python

How to use dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile",
	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/Qwen2.5-1.5B-Instruct-Q8-mobile 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/Qwen2.5-1.5B-Instruct-Q8-mobile
# Run inference directly in the terminal:
llama cli -hf dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile
# Run inference directly in the terminal:
llama cli -hf dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile

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/Qwen2.5-1.5B-Instruct-Q8-mobile
# Run inference directly in the terminal:
./llama-cli -hf dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile

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/Qwen2.5-1.5B-Instruct-Q8-mobile
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile

Use Docker

docker model run hf.co/dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile

LM Studio
Jan

vLLM

How to use dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile"
# 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/Qwen2.5-1.5B-Instruct-Q8-mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile

SGLang

How to use dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile with Ollama:
```
ollama run hf.co/dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile
```

Unsloth Studio

How to use dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile 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/Qwen2.5-1.5B-Instruct-Q8-mobile 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/Qwen2.5-1.5B-Instruct-Q8-mobile to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile to start chatting

How to use dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile

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/Qwen2.5-1.5B-Instruct-Q8-mobile"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile 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/Qwen2.5-1.5B-Instruct-Q8-mobile

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/Qwen2.5-1.5B-Instruct-Q8-mobile

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile with Docker Model Runner:
```
docker model run hf.co/dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile
```

Lemonade

How to use dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile

Run and chat with the model

lemonade run user.Qwen2.5-1.5B-Instruct-Q8-mobile-{{QUANT_TAG}}

List all available models

lemonade list

Qwen2.5-1.5B-Instruct-Q8-mobile

✅ Verified on real phone hardware — Snapdragon 865, June 2026.

Phone Benchmark (Samsung S20 FE, Snapdragon 865)

Metric	Value
Phone Speed	13.5 tokens/sec
CPU Speed	8.7 tokens/sec
File Size	1570 MB
Chat Format	chatml
Test Output	"Paris" ✅ (correct)

Usage

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama(model_path="model.gguf", chat_format="chatml", n_ctx=512, n_threads=4, verbose=False)
response = llm.create_chat_completion(
    messages=[{"role": "user", "content": "What is the capital of France?"}],
    max_tokens=50,
)
print(response["choices"][0]["message"]["content"])

dispatchAI SDK

from dispatchai import load_model
model = load_model("Qwen2.5-1.5B-Instruct-Q8-mobile", backend="gguf")
print(model.chat("What is the capital of France?"))

On Android (via ADB)

hf download dispatchAI/Qwen2.5-1.5B-Instruct-Q8-mobile model.gguf
MSYS_NO_PATHCONV=1 adb push model.gguf /data/local/tmp/
MSYS_NO_PATHCONV=1 adb shell "cd /data/local/tmp && LD_LIBRARY_PATH=/data/local/tmp ./llama-cli -m model.gguf -p 'Hello' -n 30 -t 4 -st"