NVIDIA H800 PCIe 80 GB vs NVIDIA RTX PRO 6000 Blackwell Server

Comparison of NVIDIA H800 PCIe 80 GB with 80 GB HBM2e and 14,592 cores vs NVIDIA RTX PRO 6000 Blackwell Server with 96 GB GDDR7 and 24,064 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA H800 PCIe 80 GB

44.1

NVIDIA H800 PCIe 80 GB

44.1
MI250 MI250
Instinct MI300X Instinct MI300X
RX 7900 XTX RX 7900 XTX

NVIDIA RTX PRO 6000 Blackwell Server

NVIDIA RTX PRO 6000 Blackwell Server

Contents:

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

Memory

Memory Size

🔥 80 ГБ
96 GB

Memory Type

HBM2e GDDR7

Memory Bandwidth

🔥 +14% 2.04 TB/s
1.79 TB/s

Memory Bus Width

5,120 бит 512 бит

ML Performance

FP16 (Half Precision)

🔥 +63% 204.9 TFLOPS
126.0 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 51.22 TFLOPS
126.0 TFLOPS

FP64 (Double Precision)

🔥 +1,201% 25.61 TFLOPS
1.968 TFLOPS

CUDA Cores

🔥 14,592
24,064

RT Cores

No 188

Architecture & Compatibility

GPU Architecture

Hopper Blackwell 2.0

SM (Streaming Multiprocessor)

🔥 114
188

PCIe Version

PCIe 5.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

9.0
🔥 12.0

Clocks & Performance

Base Clock

🔥 1,095
1,590

Boost Clock

🔥 1,755
2,617

Memory Clock

🔥 1,593
1,750

Power Consumption

TDP/TGP

🔥 -42% 350 W
600 W

Recommended PSU

🔥 -25% 750 W
1000 W

Power Connector

1x 16-pin 1x 16-pin

Rendering

Texture Units (TMU)

🔥 456
752

ROP

No 188

L2 Cache

🔥 50 MB
128 MB

Benchmarks

MLPerf, llama2-70b-99.9 (fp4)

3 250 tokens/s

MLPerf, llama3.1-8b (fp4)

5 758 tokens/s

Geekbench AI, FP16

53 322 points

Geekbench AI, INT8

28 264 points

Geekbench AI, FP32

37 299 points

MLPerf, mixtral-8x7b (fp8)

3 767 tokens/s

Additional

Slots

Dual-slot Dual-slot

Release Date

March 21, 2023 March 18, 2025

Display Outputs

No outputs
4x DisplayPort 2.1b

Renting is cheaper than buying