Repository: Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q6_K

This repository contains the Q6_K 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 Q6_K release is intended as the higher-quality workstation-oriented GGUF version of BuildEng 32B, preserving more reasoning quality while still remaining practical for local inference.

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

Quant type: Q6_K

Original source: merged BuildEng V8 32B model

Conversion stack: llama.cpp GGUF conversion and quantization

The Q6_K quantization was created as the higher-quality local inference release of BuildEng V8 32B for users prioritizing reasoning preservation and stronger output consistency.

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.

Thank you for everything.

Qwen/Qwen2.5-32B-Instruct

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.

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.

Example llama.cpp usage:

Example Ollama Modelfile:

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.

Irfan Uruchi

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