MI300X vs MI325X
MI325X has 1.3× the memory; MI300X rents for 1.3× less.
The AMD Instinct MI300X (CDNA 3, 2023) and the AMD Instinct MI325X (CDNA 3, 2024) share the same CDNA 3 silicon generation, so this comes down to configuration and price rather than architecture. On capacity, the MI325X carries 1.3x the memory (256 vs 192 GB), which sets what each can hold at all. Bandwidth is nearly even (5.3 vs 6 TB/s), so serving speed per GPU will be similar.
Price is where it settles: the MI300X rents from $1.85/hr against $2.40/hr for the MI325X, a 1.3x gap that the performance numbers above only partly close. Per gigabyte of VRAM, the MI325X is the cheaper rental, worth knowing if your model is capacity-bound rather than speed-bound. For how these numbers translate into tokens per dollar, the inference cost estimator runs both cards against any model. Everything below is the underlying data.
AMD · CDNA 3 · 2023
AMD Instinct MI300X
AMD's answer to Hopper: 192 GB on one GPU, a 70B model in FP16 fits with room to spare.
From $1.85/hr at Vast.ai
AMD · CDNA 3 · 2024
AMD Instinct MI325X
256 GB of HBM3e, the largest memory pool on any single accelerator you can rent.
From $2.40/hr at Vast.ai
Head to head
■ MI300X ■ MI325X, bars share one scale across the whole catalog.
| MI300X | MI325X | |
|---|---|---|
| Memory | 192 GB HBM3 | 256 GB HBM3e |
| Bandwidth | 5.3 TB/s | 6 TB/s |
| FP16 dense | 1,307 TF | 1,307 TF |
| FP8 dense | 2,614 TF | 2,614 TF |
| TDP | 750 W | 1000 W |
| Interconnect | Infinity Fabric · 896 GB/s | Infinity Fabric · 896 GB/s |
| Cheapest rental | $1.85/hr | $2.40/hr |
| $/hr per GB VRAM | $1.0¢ | $0.9¢ |
Rule of thumb: for LLM serving, prefer the GPU with more memory bandwidth per dollar; for training and prefill-heavy work, prefer FLOPS per dollar; and if the model doesn't fit in VRAM, none of the other numbers matter. Sanity-check with the VRAM calculator.