AMD Radeon RX 9060 XT 16GB vs AMD Radeon AI PRO R9700 32GB

The Radeon AI PRO R9700 delivers 87% more FP8 throughput than the Radeon RX 9060 XT (383 vs 205 TFLOPS dense). The Radeon AI PRO R9700 also carries 16 GB more memory (32 GB vs 16 GB).

Radeon RX 9060 XT: RDNA 4, 2025 Radeon AI PRO R9700: RDNA 4, 2025
FP8 dense lead
+87%
Radeon AI PRO R9700: 383 vs 205 TFLOPS
VRAM
16 vs 32 GB
16 GB more for the Radeon AI PRO R9700
Bandwidth
320 GB/s vs 640 GB/s
Radeon AI PRO R9700 moves data faster
TDP
160 W vs 300 W
Radeon RX 9060 XT draws 140 W less

Specifications

Radeon RX 9060 XT
Radeon AI PRO R9700
Architecture
RDNA 4RDNA 4
Launch Year
20252025
Form Factor
PCIePCIe
VRAM
16 GB32 GB
Memory Bandwidth
320 GB/s640 GB/s
TDP
160 W300 W
Process Node

Performance (TFLOPS)

Radeon RX 9060 XT
Radeon AI PRO R9700
FP64
No verified data available No verified data available
FP32
25.6 TFlops 47.8 TFlops
TF32
No verified data available No verified data available
BF16
No verified data available No verified data available
FP16
103.0 TFlops
205.0 TFLOPS sparse
191.0 TFlops
383.0 TFLOPS sparse
FP8
205.0 TFlops
410.0 TFLOPS sparse
383.0 TFlops
766.0 TFLOPS sparse
FP6
No verified data available No verified data available
FP4
No verified data available No verified data available
INT8
205.0 TFlops
410.0 TOPS sparse
383.0 TFlops
766.0 TOPS sparse

FLOPS by Precision

What actually differs

Both GPUs launched in 2025: the Radeon RX 9060 XT on RDNA 4 and the Radeon AI PRO R9700 on RDNA 4.

Dense throughput for the Radeon RX 9060 XT against the Radeon AI PRO R9700: FP32 26 vs 48 TFLOPS, FP16 103 vs 191 TFLOPS, FP8 205 vs 383 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 16 GB against 32 GB, fed at 320 GB/s versus 640 GB/s. More memory per GPU means larger models fit before you have to shard across cards, which often matters more than raw TFLOPS for inference.

Power budgets are 160 W for the Radeon RX 9060 XT and 300 W for the Radeon AI PRO R9700. At FP32 that works out to 0.16 against 0.16 TFLOPS per watt.

For LLM training and inference, weight the FP8 and FP16 rows and memory capacity most heavily. For scientific and HPC workloads, the FP64 row is the one to read.

Frequently asked questions

Is the Radeon RX 9060 XT faster than the Radeon AI PRO R9700?

At FP8 precision the Radeon AI PRO R9700 reaches 383 TFLOPS dense against 205 TFLOPS for the Radeon RX 9060 XT. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the Radeon RX 9060 XT or the Radeon AI PRO R9700?

The Radeon AI PRO R9700 carries 32 GB of VRAM versus 16 GB for the Radeon RX 9060 XT. Memory bandwidth is 320 GB/s for the Radeon RX 9060 XT and 640 GB/s for the Radeon AI PRO R9700.

How much power do the Radeon RX 9060 XT and the Radeon AI PRO R9700 draw?

The Radeon RX 9060 XT is rated at 160 W TDP and the Radeon AI PRO R9700 at 300 W. On FP32 throughput per watt, the Radeon RX 9060 XT is the more efficient part.

Get Comparison Updates

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