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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal 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 metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal: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 metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal: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 metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M

Use Docker

docker model run hf.co/metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M

LM Studio
Jan

vLLM

How to use metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M

Ollama
How to use metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal with Ollama:
```
ollama run hf.co/metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M
```
Unsloth Desktop

How to use metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M

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": "metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal with Docker Model Runner:
```
docker model run hf.co/metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M
```

Lemonade

How to use metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-1.5B-Instruct-AIWorksLocal-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal: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 metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal: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 "metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal: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"

Qwen2.5-1.5B-Instruct AIWorksLocal

Summary

This repository contains GGUF artifacts prepared specifically for AIWorksLocal mobile evaluation.

Release stage: Tester

Source Model Card And License

For more details on the model, license, and upstream usage requirements, please go to the original model card.

Verified Runtime

Source Hugging Face model: Qwen/Qwen2.5-1.5B-Instruct
llama.cpp build used for conversion and quantization: b8851
Verified LocalLLMClient runtime line: 0.5.0
Published repo id: metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal

Available Files

File	Quant	Size	AIWorksLocal version	Usage
`Qwen2.5-1.5B-Instruct-Q4_K_M.gguf`	Q4_K_M	940.37 MB	Unknown	Best balance, for most devices.
`Qwen2.5-1.5B-Instruct-Q6_K.gguf`	Q6_K	1.19 GB	Unknown	Near-perfect, for stronger devices.

Support Files

tokenizer.json
tokenizer_config.json
generation_config.json
config.json

Validation Notes

Unknown in the AIWorksLocal version column means the artifact is still in test.
After mobile validation, update local.json locally and rerun this publish script.

Intended Use

AIWorksLocal custom-model testing
iOS simulator, paired-device, and TestFlight validation
llama.cpp-compatible local inference workflows

Provenance

Model family: Qwen2.5-1.5B-Instruct
Source repo: Qwen/Qwen2.5-1.5B-Instruct
Source license label recorded locally: Unknown
llama.cpp build: b8851
LocalLLMClient version: 0.5.0

Downloads last month: 32

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

4-bit

6-bit

Model tree for metechsolutions/Qwen2.5-1.5B-Instruct-AIWorksLocal

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Quantized

(313)

this model