Models /Llama 3.3 70B Instruct /Can I run it?

Compatibility check

Can I run Llama 3.3 70B Instruct on GeForce RTX 3090 Ti?

No — it won't fit.

Too large

Too large

Too large

What is quantisation? →

Plan B — rent it

Llama 3.3 70B Instruct is hosted by 12 providers from $0.32 per 1M output tokens (OpenRouter).Compare providers →

Llama 3.3 70B Instruct

70.6B · full specs & benchmarks →

GeForce RTX 3090 Ti

24 GB · everything it runs →