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

Can I run gpt2-large on an RTX 4060?

Yes

Its published weights (3.25 GB) fit in the 7.20 GB an RTX 4060 can use, with room for ≈ 1K tokens of context.

Full analysis of gpt2-large Everything that runs on RTX 4060 Get the weights on Hugging Face
hf download openai-community/gpt2-large

Files and context on RTX 4060

Each file of gpt2-large (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 4060 Context (16-bit)Context (8-bit)
As published3.25 GBFits1K1K
4-bit (estimate)457 MBFits1K1K

gpt2-large on other hardware

Popular models that run on RTX 4060

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.