AMD Instinct MI325X OAM vs AMD Instinct MI300A 128GB

The Instinct MI325X is the newer part: CDNA 3, launched in 2025, against the Instinct MI300A's CDNA 3 from 2023. 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 Instinct MI325X against the Instinct MI300A: FP64 82 vs 61 TFLOPS, FP32 163 vs 123 TFLOPS, FP16 1,307 vs 981 TFLOPS, FP8 2,615 vs 1,961 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 256 GB against 128 GB, fed at 6.0 TB/s versus 5.3 TB/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.

Power budgets are 1.0 kW for the Instinct MI325X and 760 W for the Instinct MI300A. At FP32 that works out to 0.16 against 0.16 TFLOPS per watt.

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.