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

Can I run llava-1.5-7b-hf on an RTX 3060 12 GB?

Probably, at 4-bit

The published weights are too big, but a 4-bit version (about 3.97 GB) would fit, with room for an unknown amount of context. The site hasn't analyzed a GGUF of llava-1.5-7b-hf yet.

Full analysis of llava-1.5-7b-hf Everything that runs on RTX 3060 12 GB

Files and context on RTX 3060 12 GB

Each file of llava-1.5-7b-hf (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 published14.1 GBDoesn't fit——
4-bit (estimate)3.97 GBFitsnot knownnot known

llava-1.5-7b-hf 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.