excesssupply logo

Excess Supply

RTX4090x2

| 48GB VRAMs | n3-RTX-4090x2

Explore Excess Supply's RTX4090 cloud instance specifications and benchmarks. Compare hardware configurations and performance metrics to optimize your AI and ML workloads.

LLM Benchmark Comparison

Hardware Specifications

GPU ConfigurationValue
GPU TypeRTX4090
GPU InterconnectPCIE
GPU Model NameNVIDIA GeForce RTX 4090
Driver Version535.183.06
GPU VRAM48
Power Limit (W)450.00
GPU Temperature (°C)28
GPU Clock Speed (MHz)210
Memory Clock Speed (MHz)405
PstateP8
CPU ConfigurationValue
Model NameAMD EPYC 7543 32-Core Processor
Vendor IDAuthenticAMD
CPUs24
CPU Clock Speed5600.00
Threads Per Core1
Cores Per Socket12
Sockets2
MemoryValue
Total137Gb

Disks Specifications

StorageValue
Total1636.00GB

Available Disks

PropertyValue
Disk 1
Modelvda
Size100Gb
TypeHDD
Mount PointUnmounted
Disk 2
Modelvdb
Size1.5Tb
TypeHDD
Mount Point/ephemeral

Software Specifications

SoftwareValue
OSUbuntu
OS Version22.04.5 LTS (Jammy Jellyfish)
Cuda Driver12.2
Docker Version27.5.1
Python VersionPython 3.10.12

Benchmarks

powered byLLM Benchmark Logo
BenchmarkValue
ffmpeg59
Coremark (Itterations per sec)34215.328
llama2Inference (Tokens per sec)49.55
Tensorflow Mnist Training5.150

Launch instance

CloudExcess Supply
GPU TypeRTX4090
Shadeform Instance TypeRTX4090x2
Cloud Instance Typen3-RTX-4090x2
Spin Up Time10-20 mins
Hourly Price$1.20

By clicking launch you agree to our Terms of Service.

Feedback

© Shadeform, Inc