Inference Volume$52.1B+5.1%
Model Rankings165updated
AI Traffic624.8K+38.2%
Global Latency11msoptimal
API Calls102.4M+12.4%
Live Agents582,391+42.1%
AI Market Cap$58.2B+5.2%
GPU Nodes6,247+10.2%
Inference Volume$52.1B+5.1%
Model Rankings165updated
AI Traffic624.8K+38.2%
Global Latency11msoptimal
API Calls102.4M+12.4%
Live Agents582,391+42.1%
AI Market Cap$58.2B+5.2%
GPU Nodes6,247+10.2%

NVIDIA RTX 4090 24GB

NVIDIA Consumer24GB GDDR6X • 1 TB/s • 82.6 TFLOPS FP32
$1,500 - $2,2004.06%In Stock
TDP
450W
VRAM
24GB GDDR6X
Bandwidth
1.0 TB/s
Compute
82.6 FP32
Released
Oct 2022
Availability
In Stock

Description

The RTX 4090 is NVIDIA's flagship consumer GPU based on the Ada Lovelace architecture. The best GPU for AI/ML enthusiasts and local LLM inference.

Benchmarks

3DMark Time Spy
36,515
LLaMA-2 70B
28 tok/s
Stable Diffusion
12.5 it/s
Blender
12,500