ASRock RX 9060 XT Steel Legend OC 16 GB vs NVIDIA Tesla M40

Comparison of ASRock RX 9060 XT Steel Legend OC 16 GB with 16 GB GDDR6 and 2,048 cores vs NVIDIA Tesla M40 with 12 GB GDDR5 and 3,072 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

ASRock RX 9060 XT Steel Legend OC 16 GB

ASRock RX 9060 XT Steel Legend OC 16 GB

RX 7900 XTX RX 7900 XTX
Instinct MI300X Instinct MI300X
MI250 MI250

NVIDIA Tesla M40

NVIDIA Tesla M40

Contents:

Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Benchmarks Additional

Memory

Memory Size

16 GB 12 GB

Memory Type

GDDR6 GDDR5

Memory Bandwidth

322.3 GB/s 288.4 GB/s

Memory Bus Width

128 бит 384 бит

ML Performance

FP16 (Half Precision)

54.39 TFLOPS No

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

27.2 TFLOPS 6.832 TFLOPS

FP64 (Double Precision)

0.8499 TFLOPS 0.2135 TFLOPS

CUDA Cores

2,048 3,072

RT Cores

32 No

Architecture & Compatibility

GPU Architecture

RDNA 4.0 Maxwell 2.0

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 5.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

No 5.2

Clocks & Performance

Base Clock

1,900 948

Boost Clock

3,320 1,112

Memory Clock

2,518 1,502

Power Consumption

TDP/TGP

🔥 -36% 160 W
250 W

Recommended PSU

🔥 -25% 450 W
600 W

Power Connector

1x 8-pin 8-pin EPS

Rendering

Texture Units (TMU)

128 192

ROP

32 No

L2 Cache

4 MB 3 MB

Benchmarks

llama.cpp, gpt-oss 20B Q4_K - Medium

47.0 tokens/s

llama.cpp, llama 7B Q4_0

36.7 tokens/s

llama.cpp, llama-2-7b-Q4_0

41.7 tokens/s

llama.cpp, qwen3 32B Q4_K - Medium

7.19 tokens/s

llama.cpp, qwen3moe 30B.A3B Q4_K - Medium

35.1 tokens/s

Additional

Slots

Dual-slot Dual-slot

Release Date

June 4, 2025 Nov. 10, 2015

Display Outputs

1x HDMI 2.1b
2x DisplayPort 2.1a
No outputs

Renting is cheaper than buying