Apple M2 Ultra vs Apple M2
The M2 Ultra delivers 7.6x the FP32 throughput of the M2 (27 vs 3.6 TFLOPS dense). The M2 Ultra also carries 168 GB more memory (192 GB vs 24 GB).
Apple M2 Ultra
Full specs →Apple M2
Full specs →Specifications
Performance (TFLOPS)
FLOPS by Precision
What actually differs
The M2 Ultra is the newer part: Apple M2, launched in 2023, against the M2's Apple M2 from 2022. 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 M2 Ultra against the M2: FP32 27 vs 3.6 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.
Memory is 192 GB against 24 GB, fed at 800 GB/s versus 100 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 M2 Ultra faster than the M2?
At FP32 precision the M2 Ultra reaches 27 TFLOPS dense against 3.6 TFLOPS for the M2. The performance table on this page lists every published precision for both GPUs.
Which has more memory, the M2 Ultra or the M2?
The M2 Ultra carries 192 GB of VRAM versus 24 GB for the M2. Memory bandwidth is 800 GB/s for the M2 Ultra and 100 GB/s for the M2.
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.