# RTX 2000 Ada Generation Embedded GPU

> NVIDIA · Ada Lovelace

Canonical: https://gpuninja.com/chips/rtx-2000-ada-generation-embedded-gpu
Data as of: 2026-10-11T17:14:51Z
Path: Home › GPU chips
- Specs verified: 11 Oct 2026, 17:14 UTC

## Specifications

- Vendor: NVIDIA (Verified · source download.nvidia.com · retrieved 11 Oct 2026, 16:52 UTC · checked 11 Oct 2026, 17:14 UTC)
- Architecture: Ada Lovelace (Verified · source pny.com · retrieved 11 Oct 2026, 16:53 UTC · checked 11 Oct 2026, 17:14 UTC)
- Die: AD107 (Verified · source pci-ids.ucw.cz · retrieved 11 Oct 2026, 16:54 UTC · checked 11 Oct 2026, 17:14 UTC)
- Process: TSMC 4N (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 16:55 UTC · checked 11 Oct 2026, 17:14 UTC)
- Shader cores: 3,072 (Verified · source pny.com · retrieved 11 Oct 2026, 16:53 UTC · checked 11 Oct 2026, 17:14 UTC)
- Tensor cores: 96 (Verified · source pny.com · retrieved 11 Oct 2026, 16:53 UTC · checked 11 Oct 2026, 17:14 UTC)
- RT cores: 24 (Verified · source pny.com · retrieved 11 Oct 2026, 16:53 UTC · checked 11 Oct 2026, 17:14 UTC)
- Memory bus: 128-bit (Verified · source pny.com · retrieved 11 Oct 2026, 16:53 UTC · checked 11 Oct 2026, 17:14 UTC)
- Max VRAM: 8 GB (Verified · source pny.com · retrieved 11 Oct 2026, 16:53 UTC · checked 11 Oct 2026, 17:14 UTC)
- Reference boost clock: Unknown
- Reference TDP: 115 W (Verified · source nvidia.com · retrieved 11 Oct 2026, 17:13 UTC · checked 11 Oct 2026, 17:14 UTC)
- Host interface: Not recorded
- Launch MSRP: No public MSRP
- Launch date: Unknown
- Segment: Embedded (Verified · source pny.com · retrieved 11 Oct 2026, 16:53 UTC · checked 11 Oct 2026, 17:14 UTC)
- PCI IDs: 10de:28f8 (Verified · source download.nvidia.com · retrieved 11 Oct 2026, 16:52 UTC · checked 11 Oct 2026, 17:14 UTC)
- Status: Active (Verified · source nvidia.com · retrieved 11 Oct 2026, 17:13 UTC · checked 11 Oct 2026, 17:14 UTC)

## Performance

- Memory bandwidth: 256 GB/s (Verified · source pny.com · retrieved 11 Oct 2026, 16:53 UTC · checked 11 Oct 2026, 17:14 UTC)
- FP32 compute: 14.5 TFLOPS (Verified · source pny.com · retrieved 11 Oct 2026, 16:53 UTC · checked 11 Oct 2026, 17:14 UTC)
- FP16 compute: Unknown
- BF16 compute: Unknown
- FP8 compute: Unknown
- FP4 compute: Not supported
- INT8 compute: Unknown

## 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://download.nvidia.com/XFree86/Linux-x86_64/580.95.05/README/supportedchips.html — Vendor, PCI IDs; last verified 11 Oct 2026, 17:14 UTC
- https://www.pny.com/en-eu/file%20library/professional/datasheet/workstation/acmk0923_pny_ada_mxm_modules--1---1-.pdf — Architecture, Shader cores, Tensor cores, RT cores, Memory bus, Max VRAM, Segment, Memory bandwidth, FP32 compute; last verified 11 Oct 2026, 17:14 UTC
- https://pci-ids.ucw.cz/read/PC/10de/28f8 — Die; last verified 11 Oct 2026, 17:14 UTC
- https://images.nvidia.com/aem-dam/Solutions/Data-Center/l4/nvidia-ada-gpu-architecture-whitepaper-V2.02.pdf — Process; last verified 11 Oct 2026, 17:14 UTC
- https://www.nvidia.com/en-us/products/workstations/resources/rtx-embedded/ — Reference TDP, Status; last verified 11 Oct 2026, 17:14 UTC