Apple M1 Ultra vs Apple M1 Max
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).
Apple M1 Ultra
Full specs →Apple M1 Max
Full specs →Specifications
Performance (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 Ultra against the M1 Max: FP32 21 vs 10 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.
Memory is 128 GB against 64 GB, fed at 800 GB/s versus 400 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 Ultra faster than the M1 Max?
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 Ultra or the M1 Max?
The M1 Ultra carries 128 GB of VRAM versus 64 GB for the M1 Max. Memory bandwidth is 800 GB/s for the M1 Ultra and 400 GB/s for the M1 Max.
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.