Instructions to use Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0 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/qwen2.5-32b-buildeng-GGUF-Q8_0 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/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0
# Run inference directly in the terminal:
llama cli -hf Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0
# Run inference directly in the terminal:
llama cli -hf Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0

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/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0

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/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0

Use Docker

docker model run hf.co/Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0

LM Studio
Jan

vLLM

How to use Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0"
# 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/qwen2.5-32b-buildeng-GGUF-Q8_0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0

Ollama
How to use Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0 with Ollama:
```
ollama run hf.co/Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0
```
Unsloth Desktop

How to use Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0

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": "Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0 with Docker Model Runner:
```
docker model run hf.co/Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0
```

Lemonade

How to use Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0

Run and chat with the model

lemonade run user.qwen2.5-32b-buildeng-GGUF-Q8_0-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0 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/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0

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/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0

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/qwen2.5-32b-buildeng-GGUF-Q8_0:Q8_0" \
  --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"

Qwen2.5-32B BuildEng GGUF (Q8_0)

Repository: Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0

This repository contains the Q8_0 GGUF release of BuildEng V8 32B based on Qwen/Qwen2.5-32B-Instruct.

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

The model was trained to approach engineering problems cautiously rather than behaving like an overconfident general-purpose assistant. A major focus of BuildEng is inspection-first reasoning, uncertainty handling, structural risk awareness, and distinguishing observations from confirmed diagnosis.

This Q8_0 release is intended as the near-full-quality GGUF release of BuildEng 32B, preserving as much reasoning quality as possible while still remaining compatible with local GGUF inference ecosystems.

The model can be used through llama.cpp, Ollama, LM Studio, KoboldCpp, and other GGUF-compatible runtimes.

Quantization

Quant type: Q8_0

Original source: merged BuildEng V8 32B model

Conversion stack: llama.cpp GGUF conversion and quantization

The Q8_0 quantization was created as the highest-quality practical GGUF release of BuildEng V8 32B for users prioritizing reasoning preservation, stronger consistency, and near-full-quality local inference.

Dedication

This release is dedicated to my father for his birthday.

He is a civil and building engineer, and one of the main reasons I chose engineering myself. A large part of how I understand responsibility, discipline, and technical thinking comes from him.

BuildEng is my own field connected to the engineering world that inspired me growing up.

“My father is the engineer I looked up to long before I understood what engineering really meant.”

Thank you for everything.

Base Model

Qwen/Qwen2.5-32B-Instruct

Dataset

Dataset repository: Irfanuruchi/buildeng

Training dataset: BuildEng V8 Final

Total validated samples: 145,117

The BuildEng V8 dataset was designed primarily around civil and structural engineering workflows with conservative engineering reasoning behavior.

The dataset includes reinforced concrete beams, slabs, columns, footings, retaining walls, structural load paths, settlement reasoning, soil behavior, failure analysis, temporary bracing, temporary shoring, waterproofing failures, renovation unknowns, HVAC airflow reasoning, inspection workflows, uncertainty handling, contradiction handling, repair logic, multi-turn engineering diagnosis, and adversarial engineering prompts.

The dataset was intentionally structured to reduce unsafe certainty and encourage more cautious engineering behavior.

Main Behavior Goals

BuildEng 32B was trained to separate symptoms from diagnosis, avoid unsupported structural approval, request missing engineering information, reduce unsafe certainty, follow inspection-first workflows, recognize load-path concerns, identify potentially unsafe field conditions, support investigation and repair workflows, distinguish serviceability concerns from structural-capacity concerns, and respond conservatively to cracking, settlement, corrosion, deflection, demolition, moisture, and structural damage scenarios.

The model intentionally avoids behaving like an overconfident assistant.

Usage

Example llama.cpp usage:

./llama-cli \
  -m buildeng-v8-32b-Q8_0.gguf \
  -c 4096 \
  -ngl 999

Example Ollama Modelfile:

FROM ./buildeng-v8-32b-Q8_0.gguf

PARAMETER num_ctx 4096

SYSTEM """
You are BuildEng V8, a conservative civil and structural engineering assistant.
"""

Important Limitation

This model is not a licensed engineer and must not be used as final engineering approval, design certification, or construction sign-off.

It is intended for research, education, engineering-assistant workflows, drafting support, and preliminary engineering reasoning only.

Final decisions involving structural safety, demolition, occupancy, repairs, construction approval, or certification should always be reviewed and approved by a qualified licensed engineer.

Author

Irfan Uruchi

Part of my ongoing work on domain-specialized engineering language models, structural reasoning datasets, and practical civil/building engineering AI systems.

Downloads last month: 13

GGUF

Model size

33B params

Architecture

qwen2

Hardware compatibility

8-bit

Model tree for Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/Qwen2.5-32B-Instruct

Quantized

(156)

this model

Irfanuruchi
/

qwen2.5-32b-buildeng-GGUF-Q8_0

Qwen2.5-32B BuildEng GGUF (Q8_0)

Quantization

Dedication

Base Model

Dataset

Main Behavior Goals

Usage

Important Limitation

Author

Model tree for Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0

Dataset used to train Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q8_0