Can the Apple M2 Max run gpt-oss 120B?
Yes, with 96 GB or more. gpt-oss 120B needs about 67 GB and the Apple M2 Max with 96 GB of unified memory leaves about 72 GB for models. Expect about 48 tok/s, faster than you can read. The 32 and 64 GB versions don't have room.
ollama run gpt-oss:120bFirst time? Install Ollama, then paste that into a terminal.
Each Apple M2 Max version
- 32 GB (about 21 GB usable)Too big
- 64 GB (about 48 GB usable)Too big
- 96 GB (about 72 GB usable)Runs great ~48 tok/s
Speed comes from memory bandwidth: the card reads all 2.9 GB of active weights for every token. On the Apple M2 Max, Qwen3 4B runs at about 88 tok/s if you can trade some quality for speed. Cards that run gpt-oss 120B faster:
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.