NVIDIA RTX PRO 6000 Blackwell Server vs ZOTAC RTX 3060 3840SP 12 GB

Comparison of NVIDIA RTX PRO 6000 Blackwell Server with 96 GB GDDR7 and 24,064 cores vs ZOTAC RTX 3060 3840SP 12 GB with 12 GB GDDR6 and 3,840 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

ZOTAC RTX 3060 3840SP 12 GB

ZOTAC RTX 3060 3840SP 12 GB

Contents:

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

Memory

Memory Size

96 GB 12 GB

Memory Type

GDDR7 GDDR6

Memory Bandwidth

1.79 TB/s 336.0 GB/s

Memory Bus Width

512 бит 192 бит

ML Performance

FP16 (Half Precision)

126.0 TFLOPS 14.22 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

126.0 TFLOPS 14.22 TFLOPS

FP64 (Double Precision)

1.968 TFLOPS 0.2222 TFLOPS

CUDA Cores

24,064 3,840

RT Cores

188 30

Architecture & Compatibility

GPU Architecture

Blackwell 2.0 Ampere

SM (Streaming Multiprocessor)

188 30

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

🔥 12.0
8.6

Clocks & Performance

Base Clock

1,590 1,627

Boost Clock

2,617 1,852

Memory Clock

1,750 1,750

Power Consumption

TDP/TGP

600 W
🔥 -69% 185 W

Recommended PSU

1000 W
🔥 -55% 450 W

Power Connector

1x 16-pin 1x 12-pin

Rendering

Texture Units (TMU)

752 120

ROP

188 30

L2 Cache

128 MB 3 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 March 11, 2021

Display Outputs

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

Renting is cheaper than buying