AMD MI350X
vs
Nvidia H200
Two data center GPUs, one CDNA 4 and one Hopper: 288 GB HBM3e against 141 GB HBM3e and 67% more memory bandwidth on the MI350X.
At a glance
Memory
- MI350X
- 288 GB
- H200
- 141 GB
2x more on MI350X
Memory bandwidth
- MI350X
- 8.00 TB/s
- H200
- 4.80 TB/s
67% higher on MI350X
Cheapest on-demand
- MI350X
- --
- H200
- $2.09 /GPU/hr
MI350X is not sold on demand
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI350X | H200 | Difference |
|---|---|---|---|
| On-demand | No on-demand listings | $4.44 /GPU/hr from $2.09 | |
| Reserved | -- /GPU/hr from $4.76 (12 mo) | $3.68 /GPU/hr from $2.26 (1 mo) | |
| Spot | -- /GPU/hr from $4.00 | $2.62 /GPU/hr from $0.02 |
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 MI350X: 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
MI350X vs H200 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI350X | H200 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 288 GB HBM3e | 141 GB HBM3e | 2x more on MI350X |
| Bandwidth | 8,000 GB/s | 4,800 GB/s | 67% higher on MI350X |
| Bus width | 8,192-bit | ||
| Compute · dense | |||
| FP4 | 9,227.5 TFLOPS | Not supported | MI350X only |
| FP8 | 4,614 TFLOPS | 1,979 TFLOPS | 2.3x higher on MI350X |
| FP16 / BF16 | 2,309.6 TFLOPS | 989.5 TFLOPS | 2.3x higher on MI350X |
| INT8 | 4,614 TOPS | 1,979 TOPS | 2.3x higher on MI350X |
| FP32 | 144.2 TFLOPS | 67 TFLOPS | 2.2x higher on MI350X |
| FP64 | 72.1 TFLOPS | 34 TFLOPS | 2.1x higher on MI350X |
| Platform | |||
| Interconnect | Infinity Fabric 1,075 GB/s | NVLink 900 GB/s | 19% higher on MI350X |
| Board power | 1,000 W | 700 W | 43% higher on MI350X |
| Released | Q2 2025 | Q4 2023 | 2 years newer on MI350X |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16FP32FP64INT8 | FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI350X datasheet and H200 datasheet.
Where to rent them
Providers that rent these GPUs. No provider we track offers both right now.
| Provider | MI350X /GPU/hr | H200 /GPU/hr |
|---|---|---|
DigitalOcean
|
Reserved from $4.76 | -- |
Koyeb
|
-- | On-demand from $3.00 |
Lium
|
-- | On-demand from $3.00 |
GPU.ai
|
-- | On-demand from $3.29 |
Massed Compute
|
-- | On-demand from $3.62 |
Runpod
|
-- | On-demand from $3.79 |
Vast.ai
|
-- | On-demand from $3.93 |
Lyceum
|
-- | On-demand from $4.29 |
Verda
|
-- | On-demand from $4.33 |
1 provider list the MI350X and 48 the H200. Every listing is on the MI350X page and the H200 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia B200
180 GB HBM3e · released Q1 2024
From $3.75 /GPU/hr Compare
-
AMD MI355X
288 GB HBM3e · released Q2 2025
From $5.99 /GPU/hr Compare
-
AMD MI325X
256 GB HBM3e · 25% less bandwidth than the MI350X
From $2.25 /GPU/hr Compare
-
Nvidia H100
80 GB HBM3 · 30% less bandwidth than the H200
From $1.30 /GPU/hr Compare
Our data for AMD MI350X was last updated on Sept. 14, 2026, and for Nvidia H200 on Sept. 14, 2026.