Models
Docs
Pricing
Sign in
Download
Models
Download
Docs
Pricing
Sign in
numind
/
nuextract3
58
Downloads
Updated
yesterday
NuExtract3 is a 4B vision-language reasoning model by NuMind for local document understanding. Turn text and document images into structured JSON or clean Markdown with Ollama, with support for multilingual documents, OCR, and template generation.
NuExtract3 is a 4B vision-language reasoning model by NuMind for local document understanding. Turn text and document images into structured JSON or clean Markdown with Ollama, with support for multilingual documents, OCR, and template generation.
Cancel
vision
tools
thinking
Name
4 models
Size / Usage
Context
Input
nuextract3:latest
3f72674d2a65
• 9.3GB • 256K context window •
Text, Image input • yesterday
Text, Image input • yesterday
nuextract3:latest
9.3GB
256K
Text, Image
3f72674d2a65
· yesterday
nuextract3:Q4_K_M
d688f2bc1405
• 3.4GB • 256K context window •
Text, Image input • yesterday
Text, Image input • yesterday
nuextract3:Q4_K_M
3.4GB
256K
Text, Image
d688f2bc1405
· yesterday
nuextract3:Q6_K
38bc9f819605
• 4.1GB • 256K context window •
Text, Image input • yesterday
Text, Image input • yesterday
nuextract3:Q6_K
4.1GB
256K
Text, Image
38bc9f819605
· yesterday
nuextract3:bf16
3f72674d2a65
• 9.3GB • 256K context window •
Text, Image input • yesterday
Text, Image input • yesterday
nuextract3:bf16
9.3GB
256K
Text, Image
3f72674d2a65
· yesterday