Apple M1 Max vs Apple M1 Ultra

The M1 Ultra delivers 2.0x the FP32 throughput of the M1 Max (21 vs 10 TFLOPS dense). The M1 Ultra also carries 64 GB more memory (128 GB vs 64 GB).

M1 Max: Apple M1, 2021 M1 Ultra: Apple M1, 2022
FP32 dense lead
2.0x
M1 Ultra: 21 vs 10 TFLOPS
VRAM
64 vs 128 GB
64 GB more for the M1 Ultra
Bandwidth
400 GB/s vs 800 GB/s
M1 Ultra moves data faster

Specifications

M1 Max
M1 Ultra
Architecture
Apple M1Apple M1
Launch Year
20212022
Form Factor
SoCSoC
VRAM
64 GB128 GB
Memory Bandwidth
400 GB/s800 GB/s
TDP
Process Node
5nm5nm

Performance (TFLOPS)

M1 Max
M1 Ultra
FP32
10.4 TFlops 21.2 TFlops

FLOPS by Precision

What actually differs

The M1 Ultra is the newer part: Apple M1, launched in 2022, against the M1 Max's Apple M1 from 2021. Newer architectures typically add lower-precision formats and better throughput per watt, so check the precision rows your workload actually uses.

Dense throughput for the M1 Max against the M1 Ultra: FP32 10 vs 21 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 64 GB against 128 GB, fed at 400 GB/s versus 800 GB/s. More memory per GPU means larger models fit before you have to shard across cards, which often matters more than raw TFLOPS for inference.

For LLM training and inference, weight the FP8 and FP16 rows and memory capacity most heavily. For scientific and HPC workloads, the FP64 row is the one to read.

Frequently asked questions

Is the M1 Max faster than the M1 Ultra?

At FP32 precision the M1 Ultra reaches 21 TFLOPS dense against 10 TFLOPS for the M1 Max. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the M1 Max or the M1 Ultra?

The M1 Ultra carries 128 GB of VRAM versus 64 GB for the M1 Max. Memory bandwidth is 400 GB/s for the M1 Max and 800 GB/s for the M1 Ultra.

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.