llama3.3
Runs on your Mac · llama3.3
Runs on your own machine — free, offline, no key — and as a cloud API: Meta: Llama 3.3 70B Instruct.
free tools
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
What it costs
Free to run — downloads once from the Ollama library, then runs on your own Mac with no per-token cost. It costs you disk, memory and time instead — none of which the library states.
What it can do
Blank because the library states none of them. Sizes are parameter counts, not disk size — memory depends on the quantisation you pull.
Run it
In the 00 app — pick it from the local models and the app pulls it; then it answers with no key, no account, no network. Get 00.
In a terminal — with Ollama installed:
ollama pull llama3.3
It runs on your machine: no AI tokens billed, and it does not answer at the hosted endpoints. See it in the Ollama library · ← all models
Subscribe to new models