AMD MI355X
vs
Nvidia T4G
Two data center GPUs, one CDNA 4 and one Turing: 288 GB HBM3e against 16 GB GDDR6, 25x the memory bandwidth on the MI355X, and Infinity Fabric 1,075 GB/s on the MI355X where the T4G is PCIe only.
At a glance
Updated 3 minutes ago- Memory
- 288 GB
- HBM3e
- Memory bandwidth
- 8.00 TB/s
- From
- $8.60 /GPU/hr
- 4 providers
- Memory
- 16 GB
- GDDR6
- Memory bandwidth
- 320 GB/s
- From
- $0.42 /GPU/hr
- 1 provider
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | MI355X | T4G | Difference |
|---|---|---|---|
| On-demand | $8.60 | $0.42 | 20x more expensive on MI355X |
| Spot | $4.50 | No spot listings | |
| Reserved | No reserved listings | $0.18 | |
| Median | $8.60 | $1.10 | 7.8x more expensive on MI355X |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
MI355X vs T4G price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI355X | T4G | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 288 GB HBM3e | 16 GB GDDR6 | 18x more on MI355X |
| Bandwidth | 8,000 GB/s | 320 GB/s | 25x higher on MI355X |
| Bus width | 8,192-bit | 256-bit | 32x wider on MI355X |
| Compute · dense | |||
| FP4 | 10,066.3 TFLOPS | Not supported | MI355X only |
| FP8 | 5,033.2 TFLOPS | Not supported | MI355X only |
| FP16 / BF16 | 2,516.6 TFLOPS | 65 TFLOPS | 39x higher on MI355X |
| INT8 | 5,033.2 TOPS | 130 TOPS | 39x higher on MI355X |
| FP32 | 157.3 TFLOPS | 8.1 TFLOPS | 19x higher on MI355X |
| FP64 | 78.6 TFLOPS | Not supported | MI355X only |
| Platform | |||
| Interconnect | Infinity Fabric 1,075 GB/s | PCIe only | Infinity Fabric on MI355X only |
| Board power | 1,400 W | 70 W | 20x higher on MI355X |
| Released | Q2 2025 | Q3 2020 | 5 years newer on MI355X |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16FP32FP64INT8 | FP16FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI355X datasheet and T4G datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | MI355X /GPU/hr | T4G /GPU/hr |
|---|---|---|
Oracle Cloud
|
On-Demand $8.60 | -- |
DigitalOcean
|
Spot $4.50 | -- |
TensorWave
|
Custom $2.95 | -- |
Vultr
|
Spot $2.59 | -- |
AWS
|
-- | On-Demand $0.42 |
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI355X was last updated on Sept. 7, 2026, and for Nvidia T4G on Sept. 7, 2026.