---

license: other

license_name: qwen-research

license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE

language: [en]

pipeline_tag: text-generation

base_model: Qwen/Qwen2.5-3B-Instruct

base_model_relation: finetune

datasets: [Irfanuruchi/buildeng-v8-3b]

tags: [civil-engineering, structural-engineering, building-engineering, construction, qwen, engineering, text-generation, conversational]

---

BuildEng V8 3B — GGUF F16

BuildEng V8 3B GGUF F16 is the highest-precision GGUF release of BuildEng V8 3B, a domain-specialized language model focused on civil engineering, structural reasoning, construction workflows, and conservative engineering-assistant behavior.

This release is converted from:

Irfanuruchi/qwen2.5-3b-buildeng

The BuildEng V8 3B source model is fine-tuned from:

Qwen/Qwen2.5-3B-Instruct

Improved using Qwen.

Model Information

| Property | Value |

| :--- | :--- |

| Model | BuildEng V8 3B |

| Format | GGUF |

| Precision | F16 |

| BuildEng source model | Irfanuruchi/qwen2.5-3b-buildeng |

| Upstream model | Qwen/Qwen2.5-3B-Instruct |

| Domain | Civil and structural engineering |

| Primary use | High-precision local engineering-assistant inference |

The F16 release preserves substantially more numerical precision than the quantized Q8_0 and Q4_K_M variants and is intended for users who prioritize model fidelity over storage size and memory efficiency.

Focus Areas

BuildEng is designed around civil, structural, and construction-engineering workflows including:

• reinforced concrete
• masonry
• foundations and settlement
• retaining walls
• slabs, beams, and columns
• structural diagnostics
• building defects and pathology
• renovation and existing-structure uncertainty
• temporary works
• construction sequencing
• structural inspection guidance
• inspection-first reasoning
• conservative engineering recommendations

BuildEng is designed to function as an engineering assistant and to avoid presenting uncertain conclusions as established facts when important project information is missing.

Why This Version?

The GGUF F16 release is intended for users who want the highest-precision GGUF representation of BuildEng V8 3B.

Key characteristics include:

• higher numerical precision than the Q8_0 and Q4_K_M GGUF releases
• minimal loss from weight quantization
• suitable for quality-focused local inference
• useful as a high-precision GGUF reference release
• compatibility with GGUF-capable inference runtimes such as llama.cpp

For users who prioritize lower memory use and smaller model size, the Q8_0 and Q4_K_M releases are available separately.

BuildEng Model Family

| Release | Repository |

| :--- | :--- |

| Flagship 3B | Irfanuruchi/qwen2.5-3b-buildeng |

| GGUF Q4_K_M | Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q4_K_M |

| GGUF Q8_0 | Irfanuruchi/qwen2.5-3b-buildeng-GGUF-Q8_0 |

| GGUF F16 | Irfanuruchi/qwen2.5-3b-buildeng-GGUF-F16 |

| MLX 4-bit | Irfanuruchi/qwen2.5-3b-buildeng-mlx-4bit |

| MLX 8-bit | Irfanuruchi/qwen2.5-3b-buildeng-mlx-8bit |

| OpenVINO INT8 | Irfanuruchi/qwen2.5-3b-buildeng-openvino-int8 |

| OpenVINO FP16 | Irfanuruchi/qwen2.5-3b-buildeng-openvino-fp16 |

Training Dataset

Irfanuruchi/buildeng-v8-3b

Engineering Use Notice

BuildEng is an engineering-assistant model and is not a substitute for professional engineering judgment.

Model output should not be treated as:

• final structural approval
• construction authorization
• engineering certification or sign-off
• a substitute for calculations required by applicable codes or standards
• a substitute for inspection of actual site conditions
• a replacement for review by a qualified or licensed engineer where required

Engineering decisions should be independently verified using appropriate calculations, standards, drawings, site information, project-specific constraints, and professional review.

Modifications and Model Lineage

This repository contains an F16 GGUF conversion of the fine-tuned BuildEng V8 3B model.

Model lineage:

Qwen/Qwen2.5-3B-Instruct

↓

Irfanuruchi/qwen2.5-3b-buildeng

↓

Irfanuruchi/qwen2.5-3b-buildeng-GGUF-F16

The first stage represents the upstream Qwen model. The second stage represents the BuildEng V8 3B domain fine-tune. The final stage represents the F16 GGUF conversion distributed in this repository.

BuildEng-specific fine-tuning, engineering specialization, dataset development, evaluation, documentation, and related project contributions were produced by Irfan Uruchi.

Author

Irfan Uruchi

BuildEng Project