AMD MI350X
vs
Nvidia B200
Two data center GPUs, one CDNA 4 and one Blackwell: 288 GB HBM3e against 180 GB HBM3e and memory bandwidth within 5%.
At a glance
Memory
- MI350X
- 288 GB
- B200
- 180 GB
1.6x more on MI350X
Memory bandwidth
- MI350X
- 8.00 TB/s
- B200
- 7.70 TB/s
Within 5%
Cheapest on-demand
- MI350X
- --
- B200
- $3.75 /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 | B200 | Difference |
|---|---|---|---|
| On-demand | No on-demand listings | $6.52 /GPU/hr from $3.75 | |
| Reserved | -- /GPU/hr from $4.76 (12 mo) | $5.10 /GPU/hr from $3.75 | |
| Spot | -- /GPU/hr from $4.00 | $4.26 /GPU/hr from $3.95 |
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 B200 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI350X | B200 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 288 GB HBM3e | 180 GB HBM3e | 1.6x more on MI350X |
| Bandwidth | 8,000 GB/s | 7,700 GB/s | Within 5% |
| Bus width | 8,192-bit | ||
| Compute · dense | |||
| FP4 | 9,227.5 TFLOPS | 9,000 TFLOPS | Within 5% |
| FP8 | 4,614 TFLOPS | 4,500 TFLOPS | Within 5% |
| FP16 / BF16 | 2,309.6 TFLOPS | 2,250 TFLOPS | Within 5% |
| INT8 | 4,614 TOPS | 4,500 TOPS | Within 5% |
| FP32 | 144.2 TFLOPS | 75 TFLOPS | 1.9x higher on MI350X |
| FP64 | 72.1 TFLOPS | 37 TFLOPS | 1.9x higher on MI350X |
| Platform | |||
| Interconnect | Infinity Fabric 1,075 GB/s | NVLink 1,800 GB/s | 1.7x higher on B200 |
| Board power | 1,000 W | 1,000 W | Identical |
| Released | Q2 2025 | Q1 2024 | 15 months newer on MI350X |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16FP32FP64INT8 | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI350X datasheet and B200 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | MI350X /GPU/hr | B200 /GPU/hr |
|---|---|---|
DigitalOcean
|
Reserved (12mo) $4.76 | -- |
Packet·ai
|
-- | On-Demand $3.75 |
Lium
|
-- | On-Demand $5.50 |
GPU.ai
|
-- | On-Demand $6.79 |
Runpod
|
-- | On-Demand $6.79 |
Vast.ai
|
-- | On-Demand $8.75 |
Spheron
|
-- | On-Demand $9.36 |
EmpirioLabs AI
|
-- | On-Demand $11.00 |
GPUaaS
|
-- | Custom on request |
1 provider list the MI350X and 34 the B200. Every listing is on the MI350X page and the B200 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia H200
141 GB HBM3e · 40% less bandwidth than the MI350X
From $2.09 /GPU/hr Compare
-
AMD MI355X
288 GB HBM3e · released Q2 2025
From $8.60 /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 · 56% less bandwidth than the B200
From $1.30 /GPU/hr Compare
-
Nvidia B300
288 GB HBM3e · released Q1 2025
From $6.50 /GPU/hr Compare
Our data for AMD MI350X was last updated on Sept. 14, 2026, and for Nvidia B200 on Sept. 14, 2026.