Apple M1 vs Apple M1 Ultra

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 against the M1 Ultra: FP32 2.6 vs 21 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 16 GB against 128 GB, fed at 67 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.