Instructions to use HeavensHackDev/Gear-2-500m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HeavensHackDev/Gear-2-500m with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="HeavensHackDev/Gear-2-500m",
	filename="GEAR-2-500m-Identity.Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use HeavensHackDev/Gear-2-500m with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HeavensHackDev/Gear-2-500m:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf HeavensHackDev/Gear-2-500m:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HeavensHackDev/Gear-2-500m:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf HeavensHackDev/Gear-2-500m: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 HeavensHackDev/Gear-2-500m:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf HeavensHackDev/Gear-2-500m: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 HeavensHackDev/Gear-2-500m:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HeavensHackDev/Gear-2-500m:Q4_K_M

Use Docker

docker model run hf.co/HeavensHackDev/Gear-2-500m:Q4_K_M

LM Studio
Jan

vLLM

How to use HeavensHackDev/Gear-2-500m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HeavensHackDev/Gear-2-500m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HeavensHackDev/Gear-2-500m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HeavensHackDev/Gear-2-500m:Q4_K_M

Ollama
How to use HeavensHackDev/Gear-2-500m with Ollama:
```
ollama run hf.co/HeavensHackDev/Gear-2-500m:Q4_K_M
```

Unsloth Studio new

How to use HeavensHackDev/Gear-2-500m 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 HeavensHackDev/Gear-2-500m 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 HeavensHackDev/Gear-2-500m to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HeavensHackDev/Gear-2-500m to start chatting

Pi new

How to use HeavensHackDev/Gear-2-500m with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf HeavensHackDev/Gear-2-500m:Q4_K_M

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": "HeavensHackDev/Gear-2-500m:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use HeavensHackDev/Gear-2-500m with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf HeavensHackDev/Gear-2-500m: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 HeavensHackDev/Gear-2-500m:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use HeavensHackDev/Gear-2-500m with Docker Model Runner:
```
docker model run hf.co/HeavensHackDev/Gear-2-500m:Q4_K_M
```

Lemonade

How to use HeavensHackDev/Gear-2-500m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HeavensHackDev/Gear-2-500m:Q4_K_M

Run and chat with the model

lemonade run user.Gear-2-500m-Q4_K_M

List all available models

lemonade list

Model Card for GEAR-2-500m-Identity

Model Details

Model Description

GEAR-2-500m-Identity is a lightweight Transformer LLM with approximately 0.5 billion parameters, fine-tuned on the Qwen2.5 architecture using Unsloth. It is designed to run extremely fast on local machines (CPU/Edge) with minimal memory usage. The model embodies the persona of Gear, an intelligent assistant created by HeavensHack.

It is capable of code generation (Python) and general chat. While efficient, it is a small model and may struggle with complex reasoning compared to larger parameters.

Developed by: HeavensHack
Model type: Qwen2 For Causal LM
Language(s) (NLP): English, Python (Code) , (New) Russian
License: Apache 2.0
Finetuned from model: Qwen/Qwen2.5-0.5B-Instruct

Uses

Direct Use

Fast local chat assistant
Python code generation and debugging

Out-of-Scope Use

Complex mathematical reasoning
High-stakes decision making
Long-context analysis requiring high accuracy

Bias, Risks, and Limitations

Hallucinations: Due to the 0.5B parameter size, it may generate plausible but incorrect information.
Identity: The model is strictly fine-tuned to identify itself as "Gear" by HeavensHack.
Inconsistency: Behavior might be variable in long conversations.

Recommendations

Use for educational purposes, hobby projects, or low-resource environments.
Verify any code generated before running it in production.

How to Get Started

Load the model using Unsloth or standard Hugging Face transformers.
Optimized for local inference.

Training Details

Training Data: Custom identity dataset (HeavensHack), Alpaca (English), and Python Code instructions.
Training Procedure: Fine-tuned using Unsloth (LoRA) for efficiency.
Training Regime: Mixed precision (BF16/FP16).

Evaluation

Validated for identity retention and basic coding tasks.
Not benchmarked for enterprise production use.

Environmental Impact

Extremely low compute cost during training due to Unsloth optimization.

Model Card Contact

Author: HeavensHackDev

But...

At first, only the GGUF file will be available. The rest will follow later.

Downloads last month: 12

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for HeavensHackDev/Gear-2-500m

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Quantized

(206)

this model

Collection including HeavensHackDev/Gear-2-500m

Gear

Collection

The Gear family of LLMs • 2 items • Updated Dec 6, 2025