lucasjinreal/Namo-R1

A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.

35
/ 100
Emerging

This project helps anyone who needs to quickly understand or describe images without powerful graphics cards. You input an image and a text prompt, and it outputs a description, answers questions about the image, or performs tasks like multilingual optical character recognition (OCR). It's designed for users who need image intelligence on everyday computers or devices.

252 stars. No commits in the last 6 months.

Use this if you need to extract information from images, generate captions, or perform OCR on a standard CPU without specialized hardware.

Not ideal if you require extremely advanced, highly nuanced visual reasoning that typically demands much larger, GPU-accelerated models.

image-analysis document-processing content-understanding visual-search captioning
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

252

Forks

24

Language

Python

License

Last pushed

Apr 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/lucasjinreal/Namo-R1"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.