GeForce RTX 3090 Founders / reference

Specs, explained

Used for AI and consumer compute

1. 0124 GB of GDDR6X memory

   VRAM

   24 GB

   Memory type

   GDDR6X

   Memory bandwidth

   0.936 TB/s

   GDDR is graphics memory mounted on the board around the GPU rather than stacked on the package. It is widely used on graphics, rendering and cost-efficient inference cards.

   VRAM is the working space on the card. Model weights, activations and datasets have to fit in it, or be split across several GPUs. Rule of thumb for the weights alone at 16-bit precision (about 2 GB per billion parameters): up to roughly 12 billion parameters, before activations and cache. This is arithmetic on the recorded VRAM, not a benchmark.

2. 02Ampere architecture

   Architecture

   Ampere

   Generation

   GeForce RTX 30

   Launch year

   2020

   Lifecycle status

   Legacy

   Ampere brought third-generation Tensor Cores, TF32 precision and Multi-Instance GPU (MIG) to its data-center parts. (General context about the architecture, not a statement about this specific card.)

   Launched in 2020. Kovara's records list it as a legacy part.

3. 03Built to scale across GPUs

   NVLink

   Supported

   MIG

   Not supported

   Form factor

   PCIe consumer

   TDP

   350 W

   NVLink is a direct GPU-to-GPU link. Where it is supported, GPUs in the same server can exchange data faster than over PCIe alone, which matters when one training job is spread across several GPUs.

   PCIe cards slot into standard server and workstation expansion slots, which suits a wide range of systems.

   TDP is the rated thermal design power: the planning figure for power delivery and cooling in a server.

4. 04What it is used for

   Primary use (recorded)

   AI / consumer compute

   These are the uses Kovara has recorded for this part. The notes explain the workload in general terms; they are not performance claims.

   • AI
   • consumer computeCards sold for gaming and creator work that are also used for AI experiments.

Figures are Kovara master data, last verified 03 Sept 2026. Explanations describe the technology in general; they are not benchmarks and say nothing about price or availability.