NVIDIA H200 SXM 141 GB vs Sapphire R7 240 2 GB with Boost

Comparison of NVIDIA H200 SXM 141 GB with 141 GB HBM3e and 16,896 cores vs Sapphire R7 240 2 GB with Boost with 2 GB DDR3 and 320 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA H200 SXM 141 GB

NVIDIA H200 SXM 141 GB

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

Sapphire R7 240 2 GB with Boost

Sapphire R7 240 2 GB with Boost

Contents:

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

Memory

Memory Size

141 GB 2 GB

Memory Type

HBM3e DDR3

Memory Bandwidth

4.89 TB/s 25.60 GB/s

Memory Bus Width

6,144 бит 128 бит

ML Performance

FP16 (Half Precision)

267.6 TFLOPS No

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

66.91 TFLOPS 0.4992 TFLOPS

FP64 (Double Precision)

33.45 TFLOPS No

CUDA Cores

16,896 320

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Hopper GCN 1.0

SM (Streaming Multiprocessor)

132 No

PCIe Version

PCIe 5.0 x16 PCIe 3.0 x8

ML Software Support

CUDA Version

9.0 No

Clocks & Performance

Base Clock

1,500 730

Boost Clock

1,980 780

Memory Clock

1,593 800

Power Consumption

TDP/TGP

700 W
🔥 -96% 30 W

Recommended PSU

1100 W
🔥 -82% 200 W

Power Connector

8-pin EPS None

Rendering

Texture Units (TMU)

528 20

ROP

No No

L2 Cache

50 MB 256 KB

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 Single-slot

Release Date

Nov. 18, 2024 Oct. 8, 2013

Display Outputs

No outputs
1x DVI
1x HDMI 1.4a
1x VGA

Renting is cheaper than buying