GeForce RTX 3090
Save this GPU, then open another GPU page to compare them side by side.
Or compare with:
At a Glance
- Entry Type
- Reference GPU
- Architecture
- Ampere
- Series
- GeForce RTX 30 Series
- GPU Die
- GA102
- Launch Date
- 2020-09-01
- CUDA Cores
- 10,496
- TMUs
- 328
- ROPs
- 112
- Memory
- 24 GB GDDR6X
- Bus Width
- 384-bit
- TDP/TBP
- 350 W
- Rec. PSU
- 750 W
- Interface
- PCIe 4.0 x16
- Data Confidence
- Partial
Overview
GeForce RTX 3090 is an NVIDIA GPU entry in the GeForce RTX 30 Series family. It is listed with Ampere architecture and GA102 silicon.
Key reference data: 10,496 CUDA cores/shaders, 24 GB GDDR6X memory, 384-bit memory bus, 350 W board power class.
Board-partner cards can vary in cooler, PCB, display outputs, clocks, BIOS behavior, and power connector layout.
Why It Mattered
GeForce RTX 3090 is a priority page because it blurred enthusiast gaming, creator, and prosumer workloads with 24 GB of GDDR6X memory. The page should avoid treating it as a simple RTX 3080 upgrade or as a workstation replacement without source context.
Launch Context
Launch context should document NVIDIA's RTX 30 Series positioning, the 24 GB memory focus, and relationship to Titan RTX and RTX 3080 from official material and reviews.
Performance Context
Performance context should separate gaming, 8K/DLSS demos, content creation, AI, and memory-heavy workloads. Use independent reviews for actual workload conclusions.
Architecture Context
Architecture notes should explain GA102/Ampere, second-generation RT cores, third-generation Tensor cores, and why RTX 3090 differs from workstation RTX A-series cards.
Collector Relevance
For archival use, record the exact board-partner SKU, PCB revision, VBIOS, cooler, slot width, memory configuration, power connectors, display outputs, factory clocks, and any regional or OEM markings.
Used-Market Caution
Before buying used, verify the exact model and memory size, stress-test for artifacts, inspect fans, pads, screws, and power connectors, confirm display outputs, check driver support, and be wary of mined, flashed, or counterfeit listings.
Board, Connector, and Cooling Notes
Exact retail board models can differ in cooler, PCB, clocks, display outputs, BIOS behavior, and power connector layout.
Driver and Platform Notes
Driver support depends on architecture, operating system, and current NVIDIA driver branch.
Check the current NVIDIA Linux driver branch, distribution packages, and kernel compatibility for this exact GPU.
Check the current NVIDIA driver branch and OEM support policy for this exact GPU.
Reviews1 review
Board-partner, reference-card, article, and video reviews that cover this GPU.
Related GPUs
GeForce RTX 3050 4 GB
GeForce RTX 3050 6 GB
GeForce RTX 3050 8 GB
GeForce RTX 3050 8 GB GA107
SourcesPartial
Sources reviewed: 2026-06-21
This entry is still being source-checked.
Source Status
Source review pending. Treat narrative notes as incomplete until listed sources are reviewed.
Pending source review topics:
- why it mattered
- launch context
- performance context
- competitive context
- driver and platform notes
- variant notes
Data confidence and source status
Partial entry. Core specifications may be present, but history, variant notes, known issues, and source review may be incomplete.
- Verified: core specifications and historical notes have been reviewed against listed sources.
- Partial: core specifications may be present, but history, variant notes, known issues, and source review may be incomplete.
- Imported: spec-only imported entry pending editorial source review.
- Needs source review: narrative notes are incomplete until reviewed.
Primary / manufacturer sources
- NVIDIA GeForce graphics card comparisonOfficial GeForce generation and feature contextOpen source
- NVIDIA Newsroom, NVIDIA Delivers Greatest-Ever Generational Leap with GeForce RTX 30 Series GPUsPrimary launch source for RTX 3090 positioning and Ampere GeForce context.Open source
- NVIDIA, GeForce RTX 3090 Family product pageOfficial product page for 24 GB GDDR6X and RTX 3090 family framing.Open source
- NVIDIA, Ampere GA102 GPU Architecture WhitepaperPrimary architecture source for GA102/Ampere.Open source
Independent reference sources
- TechPowerUp GPU SpecsModel-level specification reference for this GPU entryOpen source
Derived datasets and spec dumps
- RightNow GPU DatabaseOpen data inventory used for bulk normalization and cross-checking Derived/spec-dump source. Treat as a reference dataset, not independent historical verification.Open source
Found an incorrect spec, missing source, or variant issue?
Submit a correction