AMD MI325X
vs
Nvidia RTX 5070
The MI325X has 21x the memory and 8.9x the bandwidth. The RTX 5070 is typically cheaper.
At a glance
Memory
21x more on MI325X
- MI325X
- 256 GB
- RTX 5070
- 12 GB
Memory bandwidth
8.9x higher on MI325X
- MI325X
- 6,000 GB/s
- RTX 5070
- 672 GB/s
Cheapest on-demand
93% cheaper on RTX 5070
- MI325X
- $2.25 /GPU/hr
- RTX 5070
- $0.17 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI325X | RTX 5070 | Difference |
|---|---|---|---|
| On-demand | $3.06 /GPU/hr from $2.25 | $0.23 /GPU/hr from $0.17 | 92% cheaper on RTX 5070 |
| Reserved | $1.95 /GPU/hr from $1.48 (12 mo) | -- /GPU/hr from $0.19 (3 mo) | |
| Spot | Sold out | -- /GPU/hr from $0.08 |
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 reserved and spot on the RTX 5070: 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
MI325X vs RTX 5070 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI325X | RTX 5070 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 256 GB HBM3e | 12 GB GDDR7 | 21x more on MI325X |
| Bandwidth | 6,000 GB/s | 672 GB/s | 8.9x higher on MI325X |
| Bus width | 8,192-bit | 192-bit | 43x wider on MI325X |
| Compute · dense | |||
| FP4 | Not supported | 493.9 TFLOPS | RTX 5070 only |
| FP8 | 2,614.9 TFLOPS | 123.5 TFLOPS | 21x higher on MI325X |
| FP16 / BF16 | 1,307.4 TFLOPS | 61.7 TFLOPS | 21x higher on MI325X |
| INT8 | 2,614.9 TOPS | 246.9 TOPS | 11x higher on MI325X |
| FP32 | 163.4 TFLOPS | 30.9 TFLOPS | 5.3x higher on MI325X |
| FP64 | 81.7 TFLOPS | Not supported | MI325X only |
| Platform | |||
| Interconnect | Infinity Fabric 896 GB/s | PCIe only | Infinity Fabric on MI325X only |
| Board power | 1,000 W | 250 W | 4x higher on MI325X |
| Released | Q4 2024 | Q1 2025 | |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI325X datasheet and RTX 5070 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.
| Provider | MI325X | RTX 5070 |
|---|---|---|
Bentaus
USA
|
$2.25 /GPU/hr On-demand | -- |
Cyfuture AI
India
|
$3.01 /GPU/hr On-demand | -- |
DigitalOcean
USA
|
$3.80 /GPU/hr On-demand | -- |
TensorWave
USA
|
$2.25 /GPU/hr Custom OAM | -- |
Vultr
USA
|
$2.00 /GPU/hr Spot | -- |
Vast.ai
USA
|
-- | $0.19 /GPU/hr On-demand |
Theta EdgeCloud
Distributed
|
-- | $0.23 /GPU/hr On-demand |
Salad
Distributed
|
-- | $0.17 /GPU/hr On-demand |
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
80 GB HBM3 · 44% less bandwidth than the MI325X
From $1.73 /GPU/hr Compare
-
Nvidia B200
180 GB HBM3e · 28% more bandwidth than the MI325X
From $3.75 /GPU/hr Compare
-
Nvidia H200
141 GB HBM3e · 20% less bandwidth than the MI325X
From $2.09 /GPU/hr Compare
-
Nvidia RTX 5060 Ti
16 GB GDDR7 · 24% less bandwidth than the RTX 5070
From $0.12 /GPU/hr Compare
-
Nvidia RTX 5070 Ti
16 GB GDDR7 · 33% more bandwidth than the RTX 5070
From $0.16 /GPU/hr Compare
Our data for AMD MI325X was last updated on Sept. 14, 2026, and for Nvidia RTX 5070 on Sept. 14, 2026.