Apple M1 Ultra vs Apple M1

The M1 Ultra is the newer part: Apple M1, launched in 2022, against the M1's Apple M1 from 2020. 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: FP32 21 vs 2.6 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 128 GB against 16 GB, fed at 800 GB/s versus 67 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.