---

license: apache-2.0

base_model:

• numind/NuExtract3

tags:

• text-generation-inference
• llama-cpp
• image-text-to-text
• transformers
• safetensors
• qwen3_5
• vision-language
• vlm
• document-understanding
• structured-extraction
• information-extraction
• ocr
• document-to-markdown
• markdown
• rag
• reasoning
• multilingual
• conversational

language:

• en

pipeline_tag: image-text-to-text

---

NuExtract3-GGUF

> NuExtract3 is NuMind's 4-billion-parameter unified vision-language model built on Qwen3.5-4B, designed for document understanding by combining strong structured information extraction with high-quality image-to-Markdown conversion, making it suitable for extraction pipelines, OCR, and RAG preprocessing across scans, receipts, forms, invoices, contracts, and tables. It accepts text, images, or both alongside a JSON template describing the desired output schema (with typed leaves like verbatim-string, date-time, currency, enums, and multi-enums), optional natural-language instructions, and optional in-context examples, and can also generate extraction templates from plain-language descriptions or convert documents directly into structured Markdown (with HTML tables and LaTeX math) — all while supporting both fast non-reasoning and deeper thinking inference modes. On NuMind's internal structured-extraction benchmark of ~600 diverse documents, NuExtract3.4-4B-RL achieves the top average score (0.651) with far fewer failed/non-deserializable outputs than larger models like Qwen3.5-9B, outperforming Gemma-4-E4B-it, GLM-4.6V-Flash, and Nemotron-3-Nano-Omni, with the paper noting that heavier reasoning actually hurts smaller models by triggering repetition loops and output-length failures. The model is deployable via vLLM with an OpenAI-compatible API supporting Multi-Token Prediction speculative decoding for faster throughput, or directly through Hugging Face Transformers, and is released under the Apache 2.0 license.

Model Files

File Name | Quant Type | File Size | File Link |

|-----------|------------|-----------|-----------|

| NuExtract3.BF16.gguf | BF16 | 8.42 GB | Download |

| NuExtract3.Q3_K_L.gguf | Q3_K_L | 2.42 GB | Download |

| NuExtract3.Q3_K_M.gguf | Q3_K_M | 2.26 GB | Download |

| NuExtract3.Q3_K_S.gguf | Q3_K_S | 2.07 GB | Download |

| NuExtract3.Q4_0.gguf | Q4_0 | 2.54 GB | Download |

| NuExtract3.Q4_K_M.gguf | Q4_K_M | 2.71 GB | Download |

| NuExtract3.Q4_K_S.gguf | Q4_K_S | 2.56 GB | Download |

| NuExtract3.Q5_0.gguf | Q5_0 | 2.99 GB | Download |

| NuExtract3.Q5_K_M.gguf | Q5_K_M | 3.07 GB | Download |

| NuExtract3.Q5_K_S.gguf | Q5_K_S | 2.99 GB | Download |

| NuExtract3.mmproj-bf16.gguf | mmproj-bf16 | 676 MB | Download |

llama.cpp

LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp