NVIDIA GeForce RTX 4090 48 GB vs NVIDIA RTX PRO 6000 Blackwell Server

Comparison NVIDIA GeForce RTX 4090 48 GB with 48 GB GDDR6X and 16,384 cores vs NVIDIA RTX PRO 6000 Blackwell Server with 96 GB GDDR7 and 24,064 cores.

Loading...

Performance Rating

NVIDIA RTX PRO 6000 Blackwell Server outperforms NVIDIA GeForce RTX 4090 48 GB by 61.52% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA GeForce RTX 4090 48 GB

35.6

NVIDIA GeForce RTX 4090 48 GB

35.6
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA RTX PRO 6000 Blackwell Server

57.5

NVIDIA RTX PRO 6000 Blackwell Server

57.5

Expert Comparison

RTX 4090 48 GB имеет больше ядер (16384 против 24064), меньшую пропускную способность памяти (1.01 TB/s против 1.79 TB/s) и более низкий TDP (450 Вт против 600 Вт). Однако у RTX PRO 6000 Blackwell Server выше производительность по индексу GPU (57.5 против 35.6) и большая память (96 ГБ против 48 ГБ). RTX 4090 лучше для игр и небольших задач, а RTX PRO 6000 Blackwell Server — для серверных задач и обработки больших данных.

Contents:

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

Memory

Memory Size

48 GB
🔥 +100% 96 ГБ

Memory Type

GDDR6X GDDR7

Memory Bandwidth

1.01 TB/s
🔥 +77% 1.79 TB/s

Memory Bus Width

384 бит 512 бит

ML Performance

FP16 (Half Precision)

82.58 TFLOPS
🔥 +53% 126.0 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

82.58 TFLOPS
🔥 +53% 126.0 TFLOPS

FP64 (Double Precision)

No
🔥 1.968 TFLOPS

CUDA Cores

16,384
🔥 +47% 24,064

RT Cores

128
🔥 +47% 188

Architecture & Compatibility

GPU Architecture

Ada Lovelace Blackwell 2.0

SM (Streaming Multiprocessor)

128
🔥 +47% 188

PCIe Version

PCIe 4.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

8.9
🔥 12.0

CUDA Toolkit (first supported)

v11 v12

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

🔥 +41% 2,235
1,590

Boost Clock

2,520
🔥 +4% 2,617

Memory Clock

1,313
🔥 +33% 1,750

Power Consumption

Recommended PSU

🔥 -15% 850 W
1000 W

Power Connector

1x 16-pin 1x 16-pin

TDP/TGP

🔥 -25% 450 W
600 W

Rendering

Texture Units (TMU)

512
🔥 +47% 752

ROP

128
🔥 +47% 188

L2 Cache

🔥 72 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

Sept. 20, 2022 March 18, 2025

Display Outputs

HDMI
DisplayPort
4x DisplayPort 2.1b

Rent on Intelion Cloud

RTX 4090 (48GB)

Available for rent on Intelion Cloud

from 81.85 RUB/hour Rent
Pay-as-you-go, per-second billing
Prices include 22% VAT
EDI & closing documents
Server ready in 3 minutes
Russian-speaking support
Card, SBP or invoice