MI300X vs H100
Comparing the MI300X and H100 for cloud rental? The MI300X is available from 0 providers starting at —, while the H100 starts at $1.14/hr across 8 providers. Below is a live breakdown of pricing, VRAM, compute throughput, and where to rent each GPU.
MI300X vs H100 at a glance
Spec profile
Each axis is scaled to the stronger GPU — the outer edge is better.
Value for money
Live pricing for both GPUs is needed to compute value-for-money metrics. See the provider tables below for current rates.
Specs are manufacturer peak FP16 Tensor figures; real-world throughput varies by workload, precision, and software stack.
MI300X vs H100 specs & pricing
| Specification | MI300X | H100 |
|---|---|---|
| Cheapest price | — | $1.14/hr |
| VRAM | 192 GB | 80 GB |
| FP16 TFLOPS | 1307 | 495 |
| Memory bandwidth | 5300 GB/s | 3350 GB/s |
| Release year | 2024 | 2023 |
| Cloud providers | — | 8 |
Which should you choose?
- •MI300X has more VRAM (192 GB), so it fits larger models and bigger batch sizes without sharding.
- •MI300X offers higher FP16 throughput, training and serving faster on compute-bound workloads.
Provider availability
Frequently asked questions
Is the MI300X or H100 cheaper to rent?
The MI300X starts at — and the H100 at $1.14/hr per GPU-hour. Prices vary by provider, region, and spot vs on-demand.
How much VRAM do the MI300X and H100 have?
The MI300X has 192 GB of VRAM and the H100 has 80 GB. More VRAM lets you serve larger models and longer context windows on a single GPU.
Which is faster, the MI300X or H100?
On paper the MI300X is faster, with 1307 FP16 TFLOPS versus 495. Real-world speed also depends on memory bandwidth and software stack.
Live prices come from public provider catalogs and can change quickly. How we collect prices.
Related GPU comparisons
Explore related GPU pages
Crawlable paths from this comparison into prices, model fit, and neighboring comparisons.