What is the biggest model the Apple M2 Ultra can run?

Qwen3 235B-A22B, which needs about 144 GB, on the 192 GB version at about 21 tok/s.

What is the biggest model the Apple M4 Max can run?

gpt-oss 120B, which needs about 67 GB, on the 128 GB version at about 66 tok/s.

Apple M2 Ultra vs Apple M4 Max for local AI

Q: Which is better for local AI, the Apple M2 Ultra or the Apple M4 Max?

The Apple M2 Ultra: it fits bigger models and runs faster. The Apple M2 Ultra fits more: up to Qwen3 235B-A22B, against gpt-oss 120B on the Apple M4 Max. The Apple M2 Ultra generates about 47% faster on any model both can run, because it has 800 GB/s of memory bandwidth to the Apple M4 Max's 546 GB/s.

The Apple M2 Ultra fits more: up to Qwen3 235B-A22B, against gpt-oss 120B on the Apple M4 Max. The Apple M2 Ultra generates about 47% faster on any model both can run, because it has 800 GB/s of memory bandwidth to the Apple M4 Max's 546 GB/s.

The numbers that matter

Memory and bandwidth

Memory decides which models fit. Bandwidth decides how fast they generate, because every token reads the model's active weights once.

	Apple M2 Ultra	Apple M4 Max
Memory	64 or 128 or 192 GB unified memory	36 or 48 or 64 or 128 GB unified memory
Usable for models	About 144 GB of 192 GB	About 96 GB of 128 GB
Bandwidth	800 GB/s	546 GB/s
Biggest model that fits	Qwen3 235B-A22B	gpt-oss 120B
Best everyday pick	Qwen3 235B-A22B, ~21 tok/s	gpt-oss 120B, ~66 tok/s

Model by model

Every model, side by side

Estimated generation speed at the largest memory size each was sold in (192 GB and 128 GB).

Model	Apple M2 Ultra	Apple M4 Max
Qwen3 4B About 4 GB	~180 tok/s Runs great	~120 tok/s Runs great
Qwen3 8B About 7 GB	~85 tok/s Runs great	~58 tok/s Runs great
Gemma 3 12B About 10 GB	~54 tok/s Runs great	~37 tok/s Runs great
Qwen3 14B About 11 GB	~47 tok/s Runs great	~32 tok/s Runs great
gpt-oss 20B About 16 GB	~140 tok/s Runs great	~96 tok/s Runs great
Gemma 3 27B About 19 GB	~26 tok/s Usable	~18 tok/s Usable
Qwen3 30B-A3B About 21 GB	~140 tok/s Runs great	~96 tok/s Runs great
Qwen3 32B About 22 GB	~22 tok/s Usable	~15 tok/s Usable
Llama 3.3 70B About 45 GB	~10 tok/s Usable	~7 tok/s Slow
gpt-oss 120B About 67 GB	~97 tok/s Runs great	~66 tok/s Runs great
Qwen3 235B-A22B About 144 GB	~21 tok/s Usable	Needs 144 GB
DeepSeek R1 671B About 406 GB	Needs 406 GB	Needs 406 GB

Which should you get?

The Apple M2 Ultra: it fits bigger models and runs faster. Price matters as much as either number: check used prices on the builds page, where every parts list has a measured or estimated speed.

How we estimate

Both columns use the same formula: memory bandwidth divided by the weights read per token, calibrated on our own rack, with Ollama's default 4-bit sizes. Real results are usually within about a third. Measured either one? Send us the number.

Compare

Other matchups

Every comparison