Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Nemotron-3.5-Parse
Modelsimage text to text model by nvidia · transformers
nvidia/Nemotron-3.5-Parse -
Youtu-Parsing-Omni
Modelsimage text to text model by tencent · transformers
tencent/Youtu-Parsing-Omni -
OXR-1.0
Modelsmodel by SoMarkAI
SoMarkAI/OXR-1.0 -
TeleOCR
Modelsimage text to text model by XingChen-AGI · transformers
XingChen-AGI/TeleOCR -
PaddleOCR-VL
Modelsimage text to text model by PaddlePaddle · PaddleOCR
PaddlePaddle/PaddleOCR-VL -
OpenThai2.0-OCR-Markdown
Modelsimage text to text model by iapp
iapp/OpenThai2.0-OCR-Markdown -
granite-docling-258M
Modelsimage text to text model by ibm-granite · transformers
ibm-granite/granite-docling-258M -
OvisOCR2
Modelsimage text to text model by ATH-MaaS · transformers
ATH-MaaS/OvisOCR2 -
dots.ocr
Modelsimage text to text model by dots-studio · dots_ocr
dots-studio/dots.ocr -
HunyuanOCR
Modelsimage text to text model by tencent · transformers
tencent/HunyuanOCR -
indra-ocr
Modelsimage to text model by datalab-to · onnx
datalab-to/indra-ocr -
Dolphin
Modelsimage text to text model by ByteDance · transformers
ByteDance/Dolphin -
PaddleOCR-VL-1.5
Modelsimage text to text model by PaddlePaddle · PaddleOCR
PaddlePaddle/PaddleOCR-VL-1.5 -
MiniCPM-OCR-1.0
Modelsimage text to text model by openbmb · minicpm-ocr
openbmb/MiniCPM-OCR-1.0 -
PaddleOCR-VL-1.6
Modelsimage text to text model by PaddlePaddle · PaddleOCR
PaddlePaddle/PaddleOCR-VL-1.6 -
Xiaomi-OCR-0
Modelsimage text to text model by xiaomi-research · transformers
xiaomi-research/Xiaomi-OCR-0 -
OvisOCR3
Modelsimage text to text model by ATH-MaaS · transformers
ATH-MaaS/OvisOCR3 -
MiniCPM-OCR-1.0-gguf
Modelsimage text to text model by openbmb
openbmb/MiniCPM-OCR-1.0-gguf -
unlimited-ocr-mlx-coreml
Modelsimage text to text model by FluidInference · mlx
FluidInference/unlimited-ocr-mlx-coreml -
Xiaomi-OCR-0
Modelsimage text to text model by SeerRay-Lab · transformers
SeerRay-Lab/Xiaomi-OCR-0 -
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
qwen/qwen3-vl-235b-a22b-instruct
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.