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

Can I run llama-3.3-70b-instruct-awq on an RTX 6000 Ada?

Yes, just

Its published weights (39.8 GB) fit in the 43.2 GB an RTX 6000 Ada can use, with room for ≈ 10K tokens of context.

Full analysis of llama-3.3-70b-instruct-awq Everything that runs on RTX 6000 Ada Get the weights on Hugging Face
hf download casperhansen/llama-3.3-70b-instruct-awq

Files and context on RTX 6000 Ada

Each file of llama-3.3-70b-instruct-awq (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 6000 Ada Context (16-bit)Context (8-bit)
As published39.8 GBTight10K20K

llama-3.3-70b-instruct-awq on other hardware

Popular models that run on RTX 6000 Ada

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.