NVIDIA RTX PRO 6000 Blackwell Server vs ZOTAC RTX 4090 D PGF

Comparison NVIDIA RTX PRO 6000 Blackwell Server with 96 GB GDDR7 and 24,064 cores vs ZOTAC RTX 4090 D PGF with 24 GB GDDR6X and 14,592 cores.

Loading...

Performance Rating

NVIDIA RTX PRO 6000 Blackwell Server outperforms ZOTAC RTX 4090 D PGF by 91.06% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA RTX PRO 6000 Blackwell Server

57.5

NVIDIA RTX PRO 6000 Blackwell Server

57.5
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

ZOTAC RTX 4090 D PGF

30.1

ZOTAC RTX 4090 D PGF

30.1

Expert Comparison

NVIDIA RTX PRO 6000 Blackwell Server обладает значительно большей памятью (96 ГБ против 24 ГБ) и пропускной способностью (1.79 TB/s против 1.01 TB/s), что делает его предпочтительным для обработки больших объемов данных и сложных вычислений. Однако ZOTAC RTX 4090 D PGF имеет более высокую производительность в FP32 (73.54 TFLOPS против 126.0 TFLOPS) и меньный TDP (425 Вт против 600 Вт), что делает его более энергоэффективным для игр и гейминга.

Contents:

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

Memory

Memory Size

🔥 +300% 96 ГБ
24 GB

Memory Type

GDDR7 GDDR6X

Memory Bandwidth

🔥 +77% 1.79 TB/s
1.01 TB/s

Memory Bus Width

512 бит 384 бит

ML Performance

FP16 (Half Precision)

🔥 +71% 126.0 TFLOPS
73.54 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +71% 126.0 TFLOPS
73.54 TFLOPS

FP64 (Double Precision)

🔥 +71% 1.968 TFLOPS
1.1491 TFLOPS

CUDA Cores

🔥 +65% 24,064
14,592

RT Cores

🔥 +65% 188
114

Architecture & Compatibility

GPU Architecture

Blackwell 2.0 Ada Lovelace

SM (Streaming Multiprocessor)

🔥 +65% 188
114

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

🔥 12.0
8.9

CUDA Toolkit (first supported)

v12 v11

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

1,590
🔥 +43% 2,280

Boost Clock

🔥 +4% 2,617
2,520

Memory Clock

🔥 +33% 1,750
1,313

Power Consumption

Recommended PSU

1000 W
🔥 -20% 800 W

Power Connector

1x 16-pin 1x 16-pin

TDP/TGP

600 W
🔥 -29% 425 W

Rendering

Texture Units (TMU)

🔥 +65% 752
456

ROP

🔥 +65% 188
114

L2 Cache

128 MB
🔥 72 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 Triple-slot

Release Date

March 18, 2025 Dec. 28, 2023

Display Outputs

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

Renting is cheaper than buying