AMD MI350P vs Nvidia RTX PRO 6000D

The MI350P has 71% more memory and 2.6x the bandwidth.

At a glance

Memory

71% more on MI350P

MI350P: 144 GB

RTX PRO 6000D: 84 GB

Memory bandwidth

2.6x higher on MI350P

MI350P: 4.00 TB/s

RTX PRO 6000D: 1.57 TB/s

Cheapest on-demand

MI350P: --

RTX PRO 6000D: $0.97 /GPU/hr

Price comparison

Median price per GPU per hour by billing type, with the cheapest listing under it.

Billing	MI350P	RTX PRO 6000D	Difference
On-demand	No on-demand listings	-- /GPU/hr from $0.97

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 on-demand on the RTX PRO 6000D: 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

MI350P vs RTX PRO 6000D price history

Weekly median on-demand price per GPU per hour

Last 5 months

Aggregating historical prices...

Specs comparison

Spec	MI350P	RTX PRO 6000D	Difference
Memory
Capacity	144 GB HBM3e	84 GB GDDR7	71% more on MI350P
Bandwidth	4,000 GB/s	1,568 GB/s	2.6x higher on MI350P
Bus width	4,096-bit	448-bit	9.1x wider on MI350P
Compute · dense
FP4	4,600 TFLOPS	1,553 TFLOPS	3x higher on MI350P
FP8	2,300 TFLOPS	776 TFLOPS	3x higher on MI350P
FP16 / BF16	1,150 TFLOPS	388 TFLOPS	3x higher on MI350P
INT8	2,300 TOPS	776 TOPS	3x higher on MI350P
FP32	72 TFLOPS	97 TFLOPS	35% higher on RTX PRO 6000D
FP64	36 TFLOPS	Not supported	MI350P only
Platform
Interconnect	PCIe only	PCIe only
Board power	600 W	400 W	50% higher on MI350P
Released	Q2 2026	Q3 2025	10 months newer on MI350P
Precision
Supported formats	FP4FP6FP8FP16BF16FP32FP64INT8	FP4FP8FP16BF16TF32FP32INT8