Apple M4 Max vs Apple M4
The M4 Max delivers 4.3x the FP32 throughput of the M4 (18 vs 4.3 TFLOPS dense). The M4 Max also carries 96 GB more memory (128 GB vs 32 GB).
Apple M4 Max
Full specs →Apple M4
Full specs →Specifications
Performance (TFLOPS)
FLOPS by Precision
What actually differs
Both GPUs launched in 2024: the M4 Max on Apple M4 and the M4 on Apple M4.
Dense throughput for the M4 Max against the M4: FP32 18 vs 4.3 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.
Memory is 128 GB against 32 GB, fed at 546 GB/s versus 120 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 M4 Max faster than the M4?
At FP32 precision the M4 Max reaches 18 TFLOPS dense against 4.3 TFLOPS for the M4. The performance table on this page lists every published precision for both GPUs.
Which has more memory, the M4 Max or the M4?
The M4 Max carries 128 GB of VRAM versus 32 GB for the M4. Memory bandwidth is 546 GB/s for the M4 Max and 120 GB/s for the M4.
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.