NVIDIA H200 SXM 141 GB vs PNY RTX 5090 ARGB EPIC-X Overclocked Triple Fan

Comparison of NVIDIA H200 SXM 141 GB with 141 GB HBM3e and 16,896 cores vs PNY RTX 5090 ARGB EPIC-X Overclocked Triple Fan with 32 GB GDDR7 and 21,760 cores.

Loading...

Performance Rating

NVIDIA H200 SXM 141 GB outperforms PNY RTX 5090 ARGB EPIC-X Overclocked Triple Fan by 45.94% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA H200 SXM 141 GB

67.4

NVIDIA H200 SXM 141 GB

67.4
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

PNY RTX 5090 ARGB EPIC-X Overclocked Triple Fan

46.2

PNY RTX 5090 ARGB EPIC-X Overclocked Triple Fan

46.2

Contents:

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

Memory

Memory Size

🔥 +341% 141 ГБ
32 ГБ

Memory Type

HBM3e GDDR7

Memory Bandwidth

🔥 +173% 4.89 TB/s
1.79 TB/s

Memory Bus Width

6,144 бит 512 бит

ML Performance

FP16 (Half Precision)

🔥 +134% 267.6 TFLOPS
114.2 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

66.91 TFLOPS
🔥 +71% 114.2 TFLOPS

FP64 (Double Precision)

🔥 +1,774% 33.45 TFLOPS
1.785 TFLOPS

CUDA Cores

16,896
🔥 +29% 21,760

RT Cores

No
🔥 170

Architecture & Compatibility

GPU Architecture

Hopper Blackwell 2.0

SM (Streaming Multiprocessor)

132
🔥 +29% 170

PCIe Version

PCIe 5.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

9.0
🔥 12.0

Clocks & Performance

Base Clock

1,500
🔥 +34% 2,017

Boost Clock

1,980
🔥 +33% 2,625

Memory Clock

1,593
🔥 +10% 1,750

Power Consumption

TDP/TGP

700 W
🔥 -18% 575 W

Recommended PSU

1100 W
🔥 -14% 950 W

Power Connector

8-pin EPS 1x 16-pin

Rendering

Texture Units (TMU)

528
🔥 +29% 680

ROP

No
🔥 170

L2 Cache

50 MB
🔥 +92% 96 MB

Benchmarks

MLPerf, llama2-70b-99.9 (UNSET)

3 534 tokens/s

MLPerf, llama2-70b-99.9 (fp16)

3 553 tokens/s

MLPerf, llama2-70b-99.9 (fp8)

2 444 tokens/s

MLPerf, llama3.1-405b (fp16)

40.8 tokens/s

MLPerf, llama3.1-405b (fp8)

25.3 tokens/s

MLPerf, llama3.1-8b (fp8)

5 161 tokens/s

MLPerf, deepseek-r1 (fp8)

1 113 tokens/s

MLPerf, mixtral-8x7b (fp8)

7 132 tokens/s

Additional

Slots

🔥 SXM Module
Triple-slot

Release Date

Nov. 18, 2024 Jan. 30, 2025

Display Outputs

No outputs
1x HDMI 2.1b
3x DisplayPort 2.1b

Renting is cheaper than buying