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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF 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 PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF: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 PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF: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 PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M

Ollama
How to use PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF with Ollama:
```
ollama run hf.co/PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF: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": "PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF with Docker Model Runner:
```
docker model run hf.co/PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M
```

Lemonade

How to use PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.PocketWeights-Qwen2.5-0.5B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF: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 PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF: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 "PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF: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"

⚡ PocketWeights: Qwen2.5-0.5B-Instruct (GGUF)

Heavy models, made light.

This repository provides high-quality, optimized GGUF quantizations of the ultra-lightweight Qwen2.5 0.5B architecture. By fusing the instruct and base models, this build aims to retain peak conversational alignment while achieving an extreme micro-footprint suitable for background tasks and edge hardware.

📖 Model Details

Architecture: Qwen2.5 (0.5 Billion Parameters)
Lineage: Fused from Qwen/Qwen2.5-0.5B-Instruct and Qwen/Qwen2.5-0.5B
Quantization Engine: llama.cpp
Target Hardware: Raspberry Pi, older smartphones, IoT edge devices, micro-controllers, and fast background agent execution.

📦 Available Files & Formats

File Name	Quant Type	Precision	Recommended Use
`model-Q4_K_M.gguf`	Q4_K_M	4-bit Medium	Maximum speed and minimal size (< 500 MB RAM).
`model-Q6_K.gguf`	Q6_K	6-bit	High fidelity with low perplexity loss.
`model-Q8_0.gguf`	Q8_0	8-bit	Near-lossless precision (Highest accuracy).

Note: You can rename these files locally to Qwen2.5-0.5B-Q4_K_M.gguf after downloading if preferred.

🚀 Quick Start Guide

Run with Ollama

You can stream and run these weights directly from Hugging Face using Ollama:

# Recommended 4-bit quantization
ollama run hf.co/PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:model-Q4_K_M

# Maximum 8-bit quality
ollama run hf.co/PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF:model-Q8_0

Run with llama.cpp

./llama-cli -m model-Q4_K_M.gguf -p "You are a helpful assistant." -cnv

🤝 Support the PocketWeights Mission

I build, verify, and maintain these quantization pipelines to provide high-quality, unrestricted, and hardware-friendly models to the open-source community for free.

Running conversion setups, cloud instances, and storage requires ongoing resources. If these weights have saved you time, compute overhead, or API bills, please consider supporting the project with a small tip!

☕ Donation Options

Ko-fi: ko-fi.com/iamvishalnarayan

Web3 / Crypto (Polygon / ETH):

0x4FC189bf839A89259dd28DE8cD97883c49e15615

Tip: Sending via the Polygon network keeps transfer gas fees below $0.01!

Downloads last month: 91

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

4-bit

6-bit

8-bit

Model tree for PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF

Base model

Qwen/Qwen2.5-0.5B

Quantized

(116)

this model