AMD Radeon PRO W6800 32GB vs AMD Ryzen AI Max 385 Radeon 8050S (Strix Halo)

The Ryzen AI Max 385 delivers 29% more FP32 throughput than the Radeon PRO W6800 (23 vs 18 TFLOPS dense). The Ryzen AI Max 385 also carries 96 GB more memory (128 GB vs 32 GB).

Radeon PRO W6800: RDNA 2, 2021 Ryzen AI Max 385: RDNA 3.5, 2025
FP32 dense lead
+29%
Ryzen AI Max 385: 23 vs 18 TFLOPS
Memory
32 vs 128 GB
96 GB more for the Ryzen AI Max 385
Bandwidth
512 GB/s vs 256 GB/s
Radeon PRO W6800 moves data faster
TDP
250 W vs 55 W
Ryzen AI Max 385 draws 195 W less
Download comparison sheet

Share this page

AMD Radeon PRO W6800 32GB vs AMD Ryzen AI Max 385 Radeon 8050S (Strix Halo)

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

Printable version →

AMD Radeon PRO W6800 32GB

Full specs →

What is the AMD Radeon PRO W6800?

The Radeon PRO W6800 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 W6800 full specifications →

Can I rent the Radeon PRO W6800 in the cloud?

Flopper is not tracking any live rental listings for the Radeon PRO W6800 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the Radeon PRO W6800 compare with other accelerators?

This page sets the Radeon PRO W6800 against the Ryzen AI Max 385. The Radeon PRO W6800 is the older generation of the two. Both are AMD parts; the Radeon PRO W6800 is a PCIe card while the Ryzen AI Max 385 is a system-on-chip. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the Radeon PRO W6800 figures come from?

Every Radeon PRO W6800 figure on this page traces to AMD's own datasheet or specification table. How Flopper verifies specifications →

AMD Ryzen AI Max 385 Radeon 8050S (Strix Halo)

Leads on FP32 Full specs →

What is the AMD Ryzen AI Max 385?

The Ryzen AI Max 385 is an APU from AMD on the RDNA 3.5 architecture, an processor that pairs CPU and GPU on one chip. It is a system-on-chip, so it is built into edge and embedded devices rather than sold as a card. Ryzen AI Max 385 full specifications →

Can I rent the Ryzen AI Max 385 in the cloud?

Flopper is not tracking any live rental listings for the Ryzen AI Max 385 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the Ryzen AI Max 385 compare with other accelerators?

This page sets the Ryzen AI Max 385 against the Radeon PRO W6800. The Ryzen AI Max 385 is the newer generation of the two. Both are AMD parts; the Ryzen AI Max 385 is a system-on-chip while the Radeon PRO W6800 is a PCIe card. Flopper also compares it head to head with the Ryzen AI Max+ 395 Radeon 8060S (Strix Halo), across every published precision, memory and power. Ryzen AI Max 385 vs Ryzen AI Max+ 395 Radeon 8060S (Strix Halo) →

Where do the Ryzen AI Max 385 figures come from?

AMD published the Ryzen AI Max 385 figures in marketing material rather than a datasheet, and Flopper has no independent confirmation of them. How Flopper verifies specifications →

Specifications

Radeon PRO W6800
Ryzen AI Max 385
Architecture
RDNA 2RDNA 3.5
Launch Year
20212025
Form Factor
PCIeSoC
Memory
32 GB128 GB
Memory Bandwidth
512 GB/s256 GB/s
TDP
250 W55 W
Process Node
7nm4nm

Performance (TFLOPS)

Radeon PRO W6800
Ryzen AI Max 385
1.1 TFLOPS No verified data available
18 TFLOPS 23 TFLOPS
No verified data available No verified data available
No verified data available No verified data available
36 TFLOPS No verified data available
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 Ryzen AI Max 385 is the newer part: RDNA 3.5 (2025) against the Radeon PRO W6800's RDNA 2 (2021).

The Ryzen AI Max 385 carries 96 GB more memory (128 GB against 32 GB), so larger models fit on one GPU before you shard. Bandwidth is 512 GB/s against 256 GB/s, which sets the ceiling on decode speed.

Power is 250 W against 55 W, and at FP32 the Ryzen AI Max 385 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.

Frequently asked questions

What is better, the Radeon PRO W6800 or the Ryzen AI Max 385?

The Ryzen AI Max 385, on throughput. At FP32 precision the Ryzen AI Max 385 reaches 23 TFLOPS dense against 18 TFLOPS for the Radeon PRO W6800. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the Radeon PRO W6800 or the Ryzen AI Max 385?

Choose the Ryzen AI Max 385 for training and high-throughput inference: it has 29% more FP32 throughput than the Radeon PRO W6800. It also carries 96 GB more memory, so larger models fit on one GPU before you shard. The Ryzen AI Max 385 draws 195 W less power, which matters in an air-cooled or power-capped rack. Packaging differs too: the Radeon PRO W6800 is a PCIe card while the Ryzen AI Max 385 is a system-on-chip, so check what your servers accept.

Which has more memory, the Radeon PRO W6800 or the Ryzen AI Max 385?

The Ryzen AI Max 385 carries 128 GB of memory versus 32 GB for the Radeon PRO W6800. Memory bandwidth is 512 GB/s for the Radeon PRO W6800 and 256 GB/s for the Ryzen AI Max 385.

How much power do the Radeon PRO W6800 and the Ryzen AI Max 385 draw?

The Radeon PRO W6800 is rated at 250 W TDP and the Ryzen AI Max 385 at 55 W. On FP32 throughput per watt, the Ryzen AI Max 385 is the more efficient part.

Get Comparison Updates

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

© 2026 Flopper.io - Compare the GPUs Powering AI