MSI RX 7700 XT MECH vs NVIDIA H200 SXM 141 GB

Comparison of MSI RX 7700 XT MECH with 12 GB GDDR6 and 3,456 cores vs NVIDIA H200 SXM 141 GB with 141 GB HBM3e and 16,896 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

MSI RX 7700 XT MECH

MSI RX 7700 XT MECH

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

NVIDIA H200 SXM 141 GB

NVIDIA H200 SXM 141 GB

Contents:

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

Memory

Memory Size

12 GB 141 GB

Memory Type

GDDR6 HBM3e

Memory Bandwidth

432.0 GB/s 4.89 TB/s

Memory Bus Width

192 бит 6,144 бит

ML Performance

FP16 (Half Precision)

71.44 TFLOPS 267.6 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

35.72 TFLOPS 66.91 TFLOPS

FP64 (Double Precision)

1.1163 TFLOPS 33.45 TFLOPS

CUDA Cores

3,456 16,896

RT Cores

54 No

Architecture & Compatibility

GPU Architecture

RDNA 3.0 Hopper

SM (Streaming Multiprocessor)

No 132

PCIe Version

PCIe 4.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

No 9.0

Clocks & Performance

Base Clock

1,603 1,500

Boost Clock

2,584 1,980

Memory Clock

2,250 1,593

Power Consumption

TDP/TGP

🔥 -65% 245 W
700 W

Recommended PSU

🔥 -50% 550 W
1100 W

Power Connector

2x 8-pin 8-pin EPS

Rendering

Texture Units (TMU)

216 528

ROP

54 No

L2 Cache

2 MB 50 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

Dual-slot SXM Module

Release Date

Aug. 25, 2023 Nov. 18, 2024

Display Outputs

1x HDMI 2.1a
2x DisplayPort 2.1
1x USB Type-C
No outputs

Renting is cheaper than buying