Instructions to use Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M 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 Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M: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 Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M: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 Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M

Use Docker

docker model run hf.co/Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M

LM Studio
Jan

vLLM

How to use Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M

Ollama
How to use Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M with Ollama:
```
ollama run hf.co/Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M
```

Unsloth Studio

How to use Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M 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 Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M 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 Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M to start chatting

How to use Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M: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": "Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M with Docker Model Runner:
```
docker model run hf.co/Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M
```

Lemonade

How to use Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M

Run and chat with the model

lemonade run user.qwen2.5-3b-buildeng-GGUF-Q4_K_M-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M: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 Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M: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 "Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M: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"

Qwen2.5-3B BuildEng GGUF Q4_K_M

Repository: Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M

This repository contains the Q4_K_M GGUF release of BuildEng V8 3B based on Qwen2.5-3B-Instruct.

BuildEng is a domain-specialized engineering language model project focused on civil engineering, structural reasoning, construction workflows, and conservative engineering-assistant behavior.

The Q4_K_M release is intended mainly for efficient local inference while still preserving strong engineering reasoning quality.

Model Information

Base model:

Qwen/Qwen2.5-3B-Instruct

Format:

GGUF

Release type:

Q4_K_M

Main focus areas include reinforced concrete, foundations, retaining walls, slabs, columns, structural diagnostics, settlement reasoning, temporary works, construction sequencing, renovation uncertainty, and inspection-first engineering workflows.

Related Repositories

Merged model:

https://huggingface.co/Irfanuruchi/qwen2.5-3b-buildeng

Q4_K_M GGUF:

https://huggingface.co/Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M

Q8_0 GGUF:

https://huggingface.co/Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q8_0

F16 GGUF:

https://huggingface.co/Irfanuruchi/qwen2.5-3b-buildeng-GGUF-F16

Dataset:

https://huggingface.co/datasets/Irfanuruchi/buildeng-v8-3b

License

This model is a fine-tune based on Qwen2.5-3B-Instruct. Due to the upstream licensing of the 3B parameter model, this specific variant is released under the Qwen Research License Agreement and is for non-commercial research and evaluation purposes only.

Branding: Built with Qwen.

(Note: If you require a BuildEng model for commercial deployment, please look at the variants based on Qwen2.5-1.5B or Qwen2.5-32B, which are Apache 2.0 licensed).

Important Notice

This model is intended for research and engineering-assistant workflows only.

It must not be used as final engineering approval, construction sign-off, or replacement for licensed engineering review.

Author

Irfan Uruchi

Downloads last month: 133

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Quantized

(264)

this model