AMD MI355X
vs
Nvidia H100
The MI355X is newer, with 3.6x the memory and 2.4x the bandwidth. The H100 is cheaper right now.
At a glance
Memory
3.6x more on MI355X
- MI355X
- 288 GB
- H100
- 80 GB
Memory bandwidth
2.4x higher on MI355X
- MI355X
- 8.00 TB/s
- H100
- 3.35 TB/s
Cheapest on-demand
70% cheaper on H100
- MI355X
- $5.99 /GPU/hr
- H100
- $1.79 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI355X | H100 | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $5.99 | $3.70 /GPU/hr from $1.79 | |
| Reserved | No reserved listings | $3.29 /GPU/hr from $1.53 (1 mo) | |
| Spot | -- /GPU/hr from $3.44 | $2.46 /GPU/hr from $1.29 |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. No median for on-demand and spot on the MI355X: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
MI355X vs H100 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI355X | H100 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 288 GB HBM3e | 80 GB HBM3 94 GB on NVL | 3.6x more on MI355X |
| Bandwidth | 8,000 GB/s | 3,350 GB/s 2,000 GB/s on PCIe 3,938 GB/s on NVL | 2.4x higher on MI355X |
| Bus width | 8,192-bit | 5,120-bit | 60% wider on MI355X |
| Compute · dense | |||
| FP4 | 10,066.3 TFLOPS | Not supported | MI355X only |
| FP8 | 5,033.2 TFLOPS | 1,979 TFLOPS | 2.5x higher on MI355X |
| FP16 / BF16 | 2,516.6 TFLOPS | 989.5 TFLOPS | 2.5x higher on MI355X |
| INT8 | 5,033.2 TOPS | 1,979 TOPS | 2.5x higher on MI355X |
| FP32 | 157.3 TFLOPS | 67 TFLOPS | 2.3x higher on MI355X |
| FP64 | 78.6 TFLOPS | 34 TFLOPS | 2.3x higher on MI355X |
| Platform | |||
| Interconnect | Infinity Fabric 1,075 GB/s | NVLink 900 GB/s NVLink 600 GB/s on PCIe, NVL | 19% higher on MI355X |
| Board power | 1,400 W | 700 W | 2x higher on MI355X |
| Released | Q2 2025 | Q3 2022 | 3 years newer on MI355X |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16FP32FP64INT8 | FP8FP16BF16TF32FP32FP64INT8 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI355X datasheet and H100 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | MI355X | H100 |
|---|---|---|
Daytona
USA
|
$5.99 /GPU/hr On-demand | $3.95 /GPU/hr On-demand |
Oracle Cloud
USA
|
$8.60 /GPU/hr On-demand | -- |
DigitalOcean
USA
|
$5.50 /GPU/hr Spot | -- |
TensorWave
USA
|
$2.95 /GPU/hr Custom OAM | -- |
Crusoe
USA
|
On request Custom | -- |
Vultr
USA
|
$2.59 /GPU/hr Spot | -- |
Lium
Distributed
|
-- | $1.79 /GPU/hr On-demand SXM |
HyperAI
Hong Kong
|
-- | $1.80 /GPU/hr On-demand |
GPU.ai
UAE
|
-- | $2.48 /GPU/hr On-demand PCIe |
Massed Compute
USA
|
-- | $2.73 /GPU/hr On-demand |
Jarvislabs
India
|
-- | $3.49 /GPU/hr On-demand SXM |
Runcrate
USA
|
-- | $3.55 /GPU/hr On-demand SXM |
Runpod
USA
|
-- | $3.99 /GPU/hr On-demand SXM |
6 providers list the MI355X and 57 the H100. Every listing is on the MI355X page and the H100 page.
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI355X was last updated on Sept. 14, 2026, and for Nvidia H100 on Sept. 14, 2026.