Flopper.io Flopper.io
vs

AMD Radeon PRO W6600 8GB vs NVIDIA P100 SXM2 16GB

The Radeon PRO W6600 and the P100 deliver near-identical FP16 throughput (21 vs 21 TFLOPS dense). The P100 also carries 8 GB more memory (16 GB vs 8 GB).

Radeon PRO W6600: RDNA 2, 2021 P100: Pascal, 2016
Memory
8 vs 16 GB
8 GB more for the P100
Bandwidth
224 GB/s vs 732 GB/s
P100 moves data faster
TDP
130 W vs 300 W
Radeon PRO W6600 draws 170 W less
Download comparison sheet

Share this page

AMD Radeon PRO W6600 8GB vs NVIDIA P100 SXM2 16GB

A post with this link shows the card on the Image tab as its preview.

Post on X Share on LinkedIn
 Printable version →

AMD Radeon PRO W6600 8GB

Full specs →

What is the AMD Radeon PRO W6600?

The Radeon PRO W6600 is a GPU from AMD on the RDNA 2 architecture, an accelerator for AI training, inference and high-performance computing. It is a PCIe add-in card, so it fits standard servers and workstations. Radeon PRO W6600 full specifications →

Can I rent the Radeon PRO W6600 in the cloud?

Flopper is not tracking any live rental listings for the Radeon PRO W6600 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the Radeon PRO W6600 compare with other accelerators?

This page sets the Radeon PRO W6600 against the P100. The Radeon PRO W6600 is the newer generation of the two. This is a cross-vendor matchup, AMD against NVIDIA; the Radeon PRO W6600 is a PCIe card while the P100 is an SXM module. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the Radeon PRO W6600 figures come from?

Every Radeon PRO W6600 figure on this page traces to AMD's own datasheet or specification table. How Flopper verifies specifications →

NVIDIA P100 SXM2 16GB

Full specs →

What is the NVIDIA P100?

The P100 is a GPU from NVIDIA on the Pascal architecture, an accelerator for AI training, inference and high-performance computing. It is an SXM module, the mezzanine format used in dense multi-GPU servers. P100 full specifications →

Can I rent the P100 in the cloud?

Flopper is not tracking any live rental listings for the P100 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the P100 compare with other accelerators?

This page sets the P100 against the Radeon PRO W6600. The P100 is the older generation of the two. This is a cross-vendor matchup, NVIDIA against AMD; the P100 is an SXM module while the Radeon PRO W6600 is a PCIe card. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the P100 figures come from?

Every P100 figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

Specifications

Radeon PRO W6600
P100
Architecture
RDNA 2Pascal
Launch Year
20212016
Form Factor
PCIeSXM
Memory
8 GB16 GB
Memory Bandwidth
224 GB/s732 GB/s
TDP
130 W300 W
Process Node
7nm16nm

Performance (TFLOPS)

Radeon PRO W6600
P100
No verified data available5.3 TFLOPS
10 TFLOPS 11 TFLOPS
No verified data available No verified data available
No verified data available No verified data available
21 TFLOPS 21 TFLOPS
No verified data available No verified data available
FP6
No verified data available No verified data available
No verified data available No verified data available
No verified data available No verified data available

Figures are dense. Where a vendor publishes a figure it sits under the dense one and never decides a winner. Hover any precision for its definition, or read the GPU glossary.

FLOPS by Precision

What actually differs

The Radeon PRO W6600 is the newer part: RDNA 2 (2021) against the P100's Pascal (2016).

The P100 carries 8 GB more memory (16 GB against 8 GB), so larger models fit on one GPU before you shard. Bandwidth is 224 GB/s against 732 GB/s, which sets the ceiling on decode speed.

Power is 130 W against 300 W, and at FP32 the Radeon PRO W6600 does more work per watt. Weight the FP8 and FP16 rows for LLM work and the FP64 row for HPC.

New to the terms? The glossary explains FP64, FP32, FP16, Sparsity and TFLOPS. For how the generations relate, see NVIDIA architectures explained.

Frequently asked questions

Is the Radeon PRO W6600 faster than the P100?

They are close on paper: both deliver about 21 TFLOPS of dense FP16 throughput. Memory, bandwidth, and power are the deciding differences.

Which should you choose, the Radeon PRO W6600 or the P100?

On raw FP16 throughput the Radeon PRO W6600 and the P100 are level, so the decision rests on memory, power and price. Choose the P100 when the model has to fit on one GPU: it carries 8 GB more memory. The Radeon PRO W6600 draws 170 W less power, which matters in an air-cooled or power-capped rack. Packaging differs too: the Radeon PRO W6600 is a PCIe card while the P100 is an SXM module, so check what your servers accept.

Which has more memory, the Radeon PRO W6600 or the P100?

The P100 carries 16 GB of memory versus 8 GB for the Radeon PRO W6600. Memory bandwidth is 224 GB/s for the Radeon PRO W6600 and 732 GB/s for the P100.

How much power do the Radeon PRO W6600 and the P100 draw?

The Radeon PRO W6600 is rated at 130 W TDP and the P100 at 300 W. On FP32 throughput per watt, the Radeon PRO W6600 is the more efficient part.

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.

Open in Full Compare Tool → Radeon PRO W6600 full specs P100 full specs Estimate cluster cost in the calculator →

© 2026 Flopper.io - Compare the GPUs Powering AI