# GeForce RTX 4090 D

> NVIDIA · Ada Lovelace

Discontinued

Canonical: https://gpuninja.com/chips/geforce-rtx-4090-d
Data as of: 2026-10-11T10:29:12Z
Path: Home › GPU chips

> **Discontinued.** Discontinued on 4 Oct 2024. This page is a preserved snapshot of the last recorded specs, prices and benchmark results.

- Specs verified: between 11 Oct 2026, 08:44 UTC and 11 Oct 2026, 10:29 UTC

## Specifications

- Vendor: NVIDIA (Verified · source nvidia.cn · retrieved 11 Oct 2026, 06:57 UTC · checked 11 Oct 2026, 08:44 UTC)
- Architecture: Ada Lovelace (Verified · source en.wikipedia.org · retrieved 11 Oct 2026, 06:56 UTC · checked 11 Oct 2026, 08:44 UTC)
- Die: AD102 (Verified · source pci-ids.ucw.cz · retrieved 11 Oct 2026, 06:55 UTC · checked 11 Oct 2026, 08:44 UTC)
- Process: TSMC 4N (Verified · source en.wikipedia.org · retrieved 11 Oct 2026, 06:56 UTC · checked 11 Oct 2026, 08:44 UTC)
- Shader cores: 14,592 (Verified · source nvidia.cn · retrieved 11 Oct 2026, 06:57 UTC · checked 11 Oct 2026, 08:44 UTC)
- Tensor cores: 456 (Verified · source en.wikipedia.org · retrieved 11 Oct 2026, 06:56 UTC · checked 11 Oct 2026, 08:44 UTC)
- RT cores: 114 (Verified · source en.wikipedia.org · retrieved 11 Oct 2026, 06:56 UTC · checked 11 Oct 2026, 08:44 UTC)
- Memory bus: 384-bit (Verified · source nvidia.cn · retrieved 11 Oct 2026, 06:57 UTC · checked 11 Oct 2026, 08:44 UTC)
- Max VRAM: 24 GB (Verified · source nvidia.cn · retrieved 11 Oct 2026, 06:57 UTC · checked 11 Oct 2026, 08:44 UTC)
- Reference boost clock: 2,520 MHz (Verified · source nvidia.cn · retrieved 11 Oct 2026, 06:57 UTC · checked 11 Oct 2026, 08:44 UTC)
- Reference TDP: 425 W (Verified · source nvidia.cn · retrieved 11 Oct 2026, 06:57 UTC · checked 11 Oct 2026, 08:44 UTC)
- Host interface: PCIe 4.0 x16 (Verified · source nvidia.cn · retrieved 11 Oct 2026, 09:48 UTC · checked 11 Oct 2026, 10:29 UTC)
- Launch MSRP: No public MSRP
- Launch date: 28 Dec 2023 (Verified · source en.wikipedia.org · retrieved 11 Oct 2026, 06:56 UTC · checked 11 Oct 2026, 08:44 UTC)
- Segment: Consumer (Verified · source nvidia.cn · retrieved 11 Oct 2026, 06:57 UTC · checked 11 Oct 2026, 08:44 UTC)
- PCI IDs: 10de:2685 (Verified · source download.nvidia.com · retrieved 11 Oct 2026, 06:55 UTC · checked 11 Oct 2026, 08:44 UTC)
- Status: Discontinued on 4 Oct 2024 (Verified · source wccftech.com · retrieved 11 Oct 2026, 06:59 UTC · checked 11 Oct 2026, 08:44 UTC)

## Performance

- Memory bandwidth: 1,008 GB/s (Verified · source en.wikipedia.org · retrieved 11 Oct 2026, 09:46 UTC · checked 11 Oct 2026, 10:29 UTC)
- FP32 compute: 73.54 TFLOPS (Verified · source en.wikipedia.org · retrieved 11 Oct 2026, 09:46 UTC · checked 11 Oct 2026, 10:29 UTC)
- FP16 compute: 147.09 TFLOPS (Unverified · source images.nvidia.com · retrieved 11 Oct 2026, 09:45 UTC · checked 11 Oct 2026, 10:29 UTC)
- BF16 compute: 147.09 TFLOPS (Unverified · source images.nvidia.com · retrieved 11 Oct 2026, 09:45 UTC · checked 11 Oct 2026, 10:29 UTC)
- FP8 compute: 294.17 TFLOPS (Unverified · source images.nvidia.com · retrieved 11 Oct 2026, 09:45 UTC · checked 11 Oct 2026, 10:29 UTC)
- FP4 compute: Not supported
- INT8 compute: 588.35 TOPS (Unverified · source images.nvidia.com · retrieved 11 Oct 2026, 09:45 UTC · checked 11 Oct 2026, 10:29 UTC)

## Boards built on this chip

Board, Chip, VRAM, TDP, Length, Slots, Price, Stock

No boards recorded for this chip.

## Benchmarks

No benchmark results recorded.

## Sources

- https://www.nvidia.cn/geforce/graphics-cards/40-series/rtx-4090-d/ — Vendor, Shader cores, Memory bus, Max VRAM, Reference boost clock, Reference TDP, Host interface, Segment; last verified 11 Oct 2026, 10:29 UTC
- https://en.wikipedia.org/wiki/GeForce_RTX_40_series — Architecture, Process, Tensor cores, RT cores, Launch date, Memory bandwidth, FP32 compute; last verified 11 Oct 2026, 10:29 UTC
- https://pci-ids.ucw.cz/read/PC/10de/2685 — Die; last verified 11 Oct 2026, 08:44 UTC
- https://download.nvidia.com/XFree86/Linux-x86_64/580.95.05/README/supportedchips.html — PCI IDs; last verified 11 Oct 2026, 08:44 UTC
- https://wccftech.com/nvidia-end-geforce-rtx-4080-super-gpu-supply-november-rtx-5090-5080-launch-simultaneously/ — Status; last verified 11 Oct 2026, 08:44 UTC
- https://images.nvidia.com/aem-dam/Solutions/geforce/ada/nvidia-ada-gpu-architecture.pdf — FP16 compute, BF16 compute, FP8 compute, INT8 compute; last verified 11 Oct 2026, 10:29 UTC