AMD MI350P
vs
Nvidia B200
The B200 has 25% more memory and 93% more bandwidth.
At a glance
Memory
25% more on B200
- MI350P
- 144 GB
- B200
- 180 GB
Memory bandwidth
93% higher on B200
- MI350P
- 4.00 TB/s
- B200
- 7.70 TB/s
Cheapest on-demand
- MI350P
- --
- B200
- $4.11 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI350P | B200 | Difference |
|---|---|---|---|
| On-demand | No on-demand listings | $8.18 /GPU/hr from $4.11 | |
| Reserved | No reserved listings | $5.56 /GPU/hr from $3.75 | |
| Spot | No spot listings | $4.78 /GPU/hr from $3.98 |
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. Verify before provisioning. More on how we price.
Price history
MI350P vs B200 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI350P | B200 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 144 GB HBM3e | 180 GB HBM3e | 25% more on B200 |
| Bandwidth | 4,000 GB/s | 7,700 GB/s | 93% higher on B200 |
| Bus width | 4,096-bit | ||
| Compute · dense | |||
| FP4 | 4,600 TFLOPS | 9,000 TFLOPS | 96% higher on B200 |
| FP8 | 2,300 TFLOPS | 4,500 TFLOPS | 96% higher on B200 |
| FP16 / BF16 | 1,150 TFLOPS | 2,250 TFLOPS | 96% higher on B200 |
| INT8 | 2,300 TOPS | 4,500 TOPS | 96% higher on B200 |
| FP32 | 72 TFLOPS | 75 TFLOPS | Within 5% |
| FP64 | 36 TFLOPS | 37 TFLOPS | Within 5% |
| Platform | |||
| Interconnect | PCIe only | NVLink 1,800 GB/s | NVLink on B200 only |
| Board power | 600 W | 1,000 W | 67% higher on B200 |
| Released | Q2 2026 | Q1 2024 | 2 years newer on MI350P |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16FP32FP64INT8 | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI350P datasheet and B200 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 | MI350P | B200 |
|---|---|---|
Runpod
USA
|
-- | $7.99 /GPU/hr On-demand SXM |
Lium
Distributed
|
-- | $8.89 /GPU/hr On-demand SXM |
GPU.ai
UAE
|
-- | $9.59 /GPU/hr On-demand SXM |
Spheron
Singapore
|
-- | $11.12 /GPU/hr On-demand SXM |
EmpirioLabs AI
USA
|
-- | $17.80 /GPU/hr On-demand |
Impossible Cloud
Germany
|
-- | $4.21 /GPU/hr Reserved SXM |
Together AI
USA
|
-- | $4.65 /GPU/hr Spot SXM |
GPUaaS
USA
|
-- | $7.00 /GPU/hr Custom |
0 providers list the MI350P and 44 the B200. Every listing is on the MI350P page and the B200 page.
Similar GPUs
Other comparisons in the same class.
-
-
Nvidia RTX PRO 6000
96 GB GDDR7 · 60% less bandwidth than the MI350P
On-demand from $0.65 /GPU/hr
-
-
Our data for AMD MI350P was last updated on Nov. 13, 2026, and for Nvidia B200 on Sept. 14, 2026.