NVIDIA RTX PRO 6000 Blackwell Server vs Palit RTX 4070 Dual

Comparison of NVIDIA RTX PRO 6000 Blackwell Server with 96 GB GDDR7 and 24,064 cores vs Palit RTX 4070 Dual with 12 GB GDDR6X and 5,888 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA RTX PRO 6000 Blackwell Server

NVIDIA RTX PRO 6000 Blackwell Server

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

Palit RTX 4070 Dual

13.2

Palit RTX 4070 Dual

13.2

Contents:

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

Memory

Memory Size

96 GB
🔥 12 ГБ

Memory Type

GDDR7 GDDR6X

Memory Bandwidth

1.79 TB/s 504.2 GB/s

Memory Bus Width

512 бит 192 бит

ML Performance

FP16 (Half Precision)

126.0 TFLOPS
🔥 29.15 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

126.0 TFLOPS
🔥 29.15 TFLOPS

FP64 (Double Precision)

1.968 TFLOPS
🔥 0.45539999999999997 TFLOPS

CUDA Cores

24,064
🔥 5,888

RT Cores

188
🔥 46

Architecture & Compatibility

GPU Architecture

Blackwell 2.0 Ada Lovelace

SM (Streaming Multiprocessor)

188
🔥 46

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

🔥 12.0
8.9

Clocks & Performance

Base Clock

1,590
🔥 +21% 1,920

Boost Clock

2,617
🔥 2,475

Memory Clock

1,750
🔥 1,313

Power Consumption

TDP/TGP

600 W
🔥 -67% 200 W

Recommended PSU

1000 W
🔥 -45% 550 W

Power Connector

1x 16-pin 1x 8-pin

Rendering

Texture Units (TMU)

752
🔥 184

ROP

188
🔥 46

L2 Cache

128 MB
🔥 36 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 18, 2025 April 12, 2023

Display Outputs

4x DisplayPort 2.1b
1x HDMI 2.1
3x DisplayPort 1.4a

Renting is cheaper than buying