NVIDIA H200 SXM 141 GB vs NVIDIA RTX A2000 12 GB

Comparison of NVIDIA H200 SXM 141 GB with 141 GB HBM3e and 16,896 cores vs NVIDIA RTX A2000 12 GB with 12 GB GDDR6 and 3,328 cores.

Loading...

Performance Rating

NVIDIA H200 SXM 141 GB outperforms NVIDIA RTX A2000 12 GB by 1,061.72% 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

NVIDIA RTX A2000 12 GB

5.8

NVIDIA RTX A2000 12 GB

5.8

Contents:

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

Memory

Memory Size

🔥 +1,075% 141 ГБ
12 ГБ

Memory Type

HBM3e GDDR6

Memory Bandwidth

🔥 4.89 TB/s
288.0 GB/s

Memory Bus Width

6,144 бит 192 бит

ML Performance

FP16 (Half Precision)

🔥 +3,250% 267.6 TFLOPS
7.987 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +738% 66.91 TFLOPS
7.987 TFLOPS

FP64 (Double Precision)

🔥 +26,703% 33.45 TFLOPS
0.1248 TFLOPS

CUDA Cores

🔥 +408% 16,896
3,328

RT Cores

No
🔥 26

Architecture & Compatibility

GPU Architecture

Hopper Ampere

SM (Streaming Multiprocessor)

🔥 +408% 132
26

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

🔥 9.0
8.6

Clocks & Performance

Base Clock

🔥 +167% 1,500
562

Boost Clock

🔥 +65% 1,980
1,200

Memory Clock

🔥 +6% 1,593
1,500

Power Consumption

TDP/TGP

700 W
🔥 -90% 70 W

Recommended PSU

1100 W
🔥 -77% 250 W

Power Connector

8-pin EPS None

Rendering

Texture Units (TMU)

🔥 +408% 528
104

ROP

No
🔥 26

L2 Cache

🔥 +1,567% 50 MB
3 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
Dual-slot

Release Date

Nov. 18, 2024 Nov. 23, 2021

Display Outputs

No outputs
4x mini-DisplayPort 1.4a

Renting is cheaper than buying