Model Anatomy See what's inside open-weight AI models

Can I run chandra-ocr-2 on an RTX 3060 12 GB?

Yes, just

Its published weights (10.6 GB) fit in the 10.8 GB an RTX 3060 12 GB can use, with room for ≈ 5K tokens of context.

Full analysis of chandra-ocr-2 Everything that runs on RTX 3060 12 GB Get the weights on Hugging Face
hf download datalab-to/chandra-ocr-2

Files and context on RTX 3060 12 GB

Each file of chandra-ocr-2 (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

FileSizeOn RTX 3060 12 GB Context (16-bit)Context (8-bit)
As published10.6 GBTight5K9K
4-bit (estimate)2.98 GBFits232K256K

chandra-ocr-2 on other hardware

Popular models that run on RTX 3060 12 GB

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.