AMD MI350P
vs
Nvidia B100
The B100 has 33% more memory and 2x the bandwidth.
At a glance
Memory
33% more on B100
- MI350P
- 144 GB
- B100
- 192 GB
Memory bandwidth
2x higher on B100
- MI350P
- 4.00 TB/s
- B100
- 8.00 TB/s
Cheapest on-demand
- MI350P
- --
- B100
- --
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
Specs comparison
| Spec | MI350P | B100 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 144 GB HBM3e | 192 GB HBM3e | 33% more on B100 |
| Bandwidth | 4,000 GB/s | 8,000 GB/s | 2x higher on B100 |
| Bus width | 4,096-bit | ||
| Compute · dense | |||
| FP4 | 4,600 TFLOPS | 7,000 TFLOPS | 52% higher on B100 |
| FP8 | 2,300 TFLOPS | 3,500 TFLOPS | 52% higher on B100 |
| FP16 / BF16 | 1,150 TFLOPS | 1,750 TFLOPS | 52% higher on B100 |
| INT8 | 2,300 TOPS | 3,500 TOPS | 52% higher on B100 |
| FP32 | 72 TFLOPS | 60 TFLOPS | 20% higher on MI350P |
| FP64 | 36 TFLOPS | 30 TFLOPS | 20% higher on MI350P |
| Platform | |||
| Interconnect | PCIe only | NVLink 1,800 GB/s | NVLink on B100 only |
| Released | Q2 2026 | Q4 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 B100 datasheet.
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 B100 on Sept. 14, 2026.