Downloads · 30 days
10
3% of all-time downloads
Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q4_K_M
qwen2.5-32b-buildeng-GGUF-Q4_K_M is a text generation model from Irfanuruchi. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Repository: Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q4KM
Downloads · 30 days
10
3% of all-time downloads
All-time downloads
332
Public
Repo size
39.7 GB
Likes
0
Public
Click a slice to open those files.
.gguf19.9 GB · 100%
From the Hugging Face model README
Repository: Irfanuruchi/qwen2.5-32b-buildeng-GGUF-Q4_K_M
This repository contains the GGUF Q4_K_M quantized 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 instead of behaving like an overconfident general-purpose assistant. The primary focus is inspection-first reasoning, uncertainty handling, structural risk awareness, and separating symptoms from confirmed diagnosis.
This GGUF release allows the model to run through llama.cpp, Ollama, LM Studio, KoboldCpp, and other GGUF-compatible inference frameworks.
Quant type: Q4_K_M
Original source: merged BuildEng V8 32B model
Conversion stack: llama.cpp GGUF conversion and quantization
The Q4_K_M quantization was selected as the primary public GGUF release because it provides a strong balance between reasoning quality, memory usage, and inference performance.
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.
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:
The model intentionally avoids behaving like an overconfident assistant.
Example llama.cpp usage:
./llama-cli \
-m buildeng-v8-32b-Q4_K_M.gguf \
-c 4096 \
-ngl 999
Example Ollama Modelfile:
FROM ./buildeng-v8-32b-Q4_K_M.gguf
PARAMETER num_ctx 4096
SYSTEM """
You are BuildEng V8, a conservative civil and structural engineering assistant.
"""
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.