LightOnOCR 1B 1025 AIO GGUF
> The LightOnOCR-1B-1025 from lightonai is a compact 1B-parameter end-to-end vision-language model optimized for Optical Character Recognition (OCR) and document understanding, combining a Pixtral-based Vision...
Model source
- Kind
- Other
- File size
- 417 MB–2.81 GB
- Base model
- lightonai/LightOnOCR-1B-1025
- Version
- vRevision a770bea
- Updated
- Sep 17, 2026
- Downloads
- 218
- Tasks
- Captioning
- Source
- Hugging Face
Source description
LightOnOCR-1B-1025-AIO-GGUF
The LightOnOCR-1B-1025 from lightonai is a compact 1B-parameter end-to-end vision-language model optimized for Optical Character Recognition (OCR) and document understanding, combining a Pixtral-based Vision Transformer encoder with a lightweight Qwen3-based text decoder distilled from high-quality VLMs, achieving state-of-the-art accuracy in its class on Olmo-Bench (76.1% overall, with 81.4% on ArXiv papers, 71.6% on old scans, and strong math/table handling) while processing 5.71 pages/second on a single H100 GPU—5× faster than dots.ocr, 2× faster than PaddleOCR-VL-0.9B, and 1.73× faster than DeepSeekOCR at under $0.01 per 1,000 pages. Fully differentiable without external OCR pipelines, it excels at layout-aware extraction from high-resolution PDFs (rendered at ~1540px longest dimension), handling tables, receipts, forms, multi-column layouts, math notation, and multilingual text (Latin-dominant) under Apache 2.0 license, with compact 32k/16k vocab variants for European languages and vLLM/Transformers support for efficient inference and LoRA fine-tuning.
LightOnOCR-1B-1025 [GGUF]
| File Name | Quant Type | File Size | File Link |
|---|---|---|---|
| LightOnOCR-1B-1025.BF16.gguf | BF16 | 1.51 GB | Download |
| LightOnOCR-1B-1025.F16.gguf | F16 | 1.51 GB | Download |
| LightOnOCR-1B-1025.F32.gguf | F32 | 3.01 GB | Download |
| LightOnOCR-1B-1025.Q8_0.gguf | Q8_0 | 805 MB | Download |
| LightOnOCR-1B-1025.mmproj-bf16.gguf | mmproj-bf16 | 821 MB | Download |
| LightOnOCR-1B-1025.mmproj-f16.gguf | mmproj-f16 | 819 MB | Download |
| LightOnOCR-1B-1025.mmproj-f32.gguf | mmproj-f32 | 1.64 GB | Download |
| LightOnOCR-1B-1025.mmproj-q8_0.gguf | mmproj-q8_0 | 437 MB | Download |
Quants Usage
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
image.png
Sources
1 source
Sources
1 sourceVerified Sep 17
Model artifacts
8 artifacts
Model artifacts
8 artifactsSource excerpts
2 excerpts
Source excerpts
2 excerpts--- license: apache-2.0 language: - en - fr - de - es - it - nl - pt - sv - da base_model: - lightonai/LightOnOCR-1B-1025 pipeline_tag: image-to-text library_name: transformers tags: - text-generation-inference - document-understanding - OCR --- # **LightOnOCR-1B-1025-AIO-GGUF** > The [LightOnOCR-1B-1025](https://huggingface.co/lightonai/LightOnOCR-1B-1025) from lightonai is a compact 1B-parameter end-to-end vision-language model optimized for Optical Character Recognition (OCR) and document understanding, combining a Pixtral-based Vision Transformer encoder with a lightweight Qwen3-based text decoder distilled from high-quality VLMs, achieving state-of-the-art accuracy in its class on Olmo-Bench (76.1% overall, with 81.4% on ArXiv papers, 71.6% on old scans, and strong math/table handling) while processing 5.71 pages/second on a single H100 GPU—5× faster than dots.ocr, 2× faster than PaddleOCR-VL-0.9B, and 1.73× faster than DeepSeekOCR at under $0.01 per 1,000 pages. Fully differentiable without external OCR pipelines, it excels at layout-aware extraction from high-resolution PDFs (rendered at ~1540px longest dimension), handling tables, receipts, forms, multi-column layouts, math notation, and multilingual text (Latin-dominant) under Apache 2.0 license, with compact 32k/16k vocab variants for European languages and vLLM/Transformers support for efficient inference and LoRA fine-tuning. ## LightOnOCR-1B-1025 [GGUF] | File Name | Quant Type | File Size | File Link | | - | - | - | - | | LightOnOCR-1B-1025.BF16.gguf | BF16 | 1.51 GB | [Download](https://huggingface.co/prithivMLmods/LightOnOCR-1B-1025-AIO-GGUF/blob/main/LightOnOCR-1B-1025.BF16.gguf) | | LightOnOCR-1B-1025.F16.gguf | F16 | 1.51 GB | [Download](https://huggingface.co/prithivMLmods/LightOnOCR-1B-1025-AIO-GGUF/blob/main/LightOnOCR-1B-1025.F16.gguf) | | LightOnOCR-1B-1025.F32.gguf | F32 | 3.01 GB | [Download](https://huggingface.co/prithivMLmods/LightOnOCR-1B-1025-AIO-GGUF/blob/main/LightOnOCR-1B-1025.F32.gguf) | | LightOnOCR-1B-1025.Q8_0.gguf | Q8_0 | 805 MB | [Download](https://huggingface.co/prithivMLmods/LightOnOCR-1B-1025-AIO-GGUF/blob/main/LightOnOCR-1B-1025.Q8_0.gguf) | | LightOnOCR-1B-1025.mmproj-bf16.gguf | mmproj-bf16 | 821 MB | [Download](https://huggingface.co/prithivMLmods/LightOnOCR-1B-1025-AIO-GGUF/blob/main/LightOnOCR-1B-1025.mmproj-bf16.gguf) | | LightOnOCR-1B-1025.mmproj-f16...
Source context: 218 downloads · 3 likes · Pipeline image-to-text · Library transformers · Repo prithivMLmods/LightOnOCR-1B-1025-AIO-GGUF
