AI & ML interests
Interactive NLP development
Recent Activity
Organization Card
We are an LLM-provider startup, specialized in document extraction, building the NuExtract Platform.
We also build open-source information extraction VLMs that we share here. They are generally SOTA in their category, and always under MIT license or Apache 2.0; use them without restrictions 🙂.
models 47
numind/NuExtract3-FP8
Image-to-Text • 5B • Updated • 958 • 3
numind/NuExtract3-GGUF
Image-Text-to-Text • Updated • 643 • 3
numind/NuExtract3
Image-to-Text • 5B • Updated • 3.32k • 55
numind/NuExtract3-W4A16
Image-Text-to-Text • 2B • Updated • 28 • 1
numind/NuExtract3-W8A8
Image-Text-to-Text • 5B • Updated • 24 • 2
numind/NuMarkdown-8B-Thinking-mlx-4bits
Image-to-Text • Updated • 41 • 3
numind/NuMarkdown-8B-Thinking-mlx-8bits
Image-to-Text • Updated • 66 • 5
numind/NuMarkdown-8B-Thinking
Image-to-Text • 8B • Updated • 63.6k • 453
numind/NuExtract-2.0-8B-GGUF
Image-Text-to-Text • 8B • Updated • 1.38k • 4
numind/NuExtract-2.0-4B-GGUF
Image-Text-to-Text • 3B • Updated • 1.13k • 3