Can the Apple M1 Ultra run Llama 3.3 70B?
Yes. Llama 3.3 70B needs about 45 GB and the Apple M1 Ultra with 64 GB of unified memory leaves about 48 GB for models. Expect about 10 tok/s, about reading speed.
ollama run llama3.3:70bFirst time? Install Ollama, then paste that into a terminal.
Llama 3.3 70B needsAbout 45 GB
Apple M1 Ultra has64 or 128 GB unified memory
Bandwidth800 GB/s
Estimated speed~10 tok/s
By memory size
Each Apple M1 Ultra version
- 64 GB (about 48 GB usable)Usable ~10 tok/s
- 128 GB (about 96 GB usable)Usable ~10 tok/s
Want it faster?
Speed comes from memory bandwidth: the card reads all 43 GB of active weights for every token. On the Apple M1 Ultra, gpt-oss 120B runs at about 97 tok/s if you can trade some quality for speed. Cards that run Llama 3.3 70B faster:
How we estimate
Speed is roughly memory bandwidth divided by the weights read per token, calibrated on our own rack. Sizes are Ollama's default 4-bit downloads plus about 1.2 GB for context. Real results are usually within about a third. Measured it yourself? Send us the number.
Keep going