# L40

> NVIDIA · Ada Lovelace

Discontinued

Canonical: https://gpuninja.com/chips/l40
Data as of: 2026-10-11T17:10:00Z
Path: Home › GPU chips

> **Discontinued.** Discontinued on 10 Nov 2025. This page is a preserved snapshot of the last recorded specs, prices and benchmark results.

- Specs verified: between 11 Oct 2026, 08:50 UTC and 11 Oct 2026, 17:10 UTC

## Specifications

- Vendor: NVIDIA (Verified · source nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Architecture: Ada Lovelace (Verified · source nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Die: AD102 (Verified · source pci-ids.ucw.cz · retrieved 11 Oct 2026, 07:04 UTC · checked 11 Oct 2026, 08:50 UTC)
- Process: TSMC 4N (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Shader cores: 18,176 (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Tensor cores: 568 (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- RT cores: 142 (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Memory bus: 384-bit (Verified · source nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Max VRAM: 48 GB (Verified · source nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Reference boost clock: 2,490 MHz (Verified · source nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Reference TDP: 300 W (Verified · source nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Host interface: PCIe 4.0 x16 (Verified · source lenovopress.lenovo.com · retrieved 11 Oct 2026, 09:50 UTC · checked 11 Oct 2026, 10:29 UTC)
- Launch MSRP: No public MSRP
- Launch date: 20 Sep 2022 (Verified · source nvidianews.nvidia.com · retrieved 11 Oct 2026, 07:13 UTC · checked 11 Oct 2026, 08:50 UTC)
- Segment: Data center (Verified · source nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- PCI IDs: 10de:26b5 (Verified · source download.nvidia.com · retrieved 11 Oct 2026, 07:01 UTC · checked 11 Oct 2026, 08:50 UTC)
- Status: Discontinued on 10 Nov 2025 (Verified · source viperatech.com · retrieved 11 Oct 2026, 16:47 UTC · checked 11 Oct 2026, 17:10 UTC)

## Performance

- Memory bandwidth: 864 GB/s (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 09:47 UTC · checked 11 Oct 2026, 10:29 UTC)
- FP32 compute: 90.5 TFLOPS (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 09:47 UTC · checked 11 Oct 2026, 10:29 UTC)
- FP16 compute: 181.05 TFLOPS (Verified · source lenovopress.lenovo.com · retrieved 11 Oct 2026, 09:50 UTC · checked 11 Oct 2026, 10:29 UTC)
- BF16 compute: 181.05 TFLOPS (Verified · source lenovopress.lenovo.com · retrieved 11 Oct 2026, 09:50 UTC · checked 11 Oct 2026, 10:29 UTC)
- FP8 compute: 362 TFLOPS (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 09:47 UTC · checked 11 Oct 2026, 10:29 UTC)
- FP4 compute: Not supported
- INT8 compute: 362 TOPS (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 09:47 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.com/en-us/data-center/l40/ — Vendor, Architecture, Segment; last verified 11 Oct 2026, 08:50 UTC
- https://pci-ids.ucw.cz/read/PC/10de/26b5 — Die; last verified 11 Oct 2026, 08:50 UTC
- https://images.nvidia.com/aem-dam/Solutions/Data-Center/l4/nvidia-ada-gpu-architecture-whitepaper-V2.02.pdf — Process, Shader cores, Tensor cores, RT cores; last verified 11 Oct 2026, 08:50 UTC
- https://www.nvidia.com/content/dam/en-zz/Solutions/Data-Center/datasheets/L-40/product-brief-L40.pdf — Memory bus, Max VRAM, Reference boost clock, Reference TDP; last verified 11 Oct 2026, 08:50 UTC
- https://lenovopress.lenovo.com/lp1718-nvidia-l40-48gb-pcie-gen4-passive-gpu — Host interface, FP16 compute, BF16 compute; last verified 11 Oct 2026, 10:29 UTC
- https://nvidianews.nvidia.com/news/nvidia-announces-ovx-computing-systems-the-graphics-and-simulation-foundation-for-the-metaverse-powered-by-ada-lovelace-gpu — Launch date; last verified 11 Oct 2026, 08:50 UTC
- https://download.nvidia.com/XFree86/Linux-x86_64/580.95.05/README/supportedchips.html — PCI IDs; last verified 11 Oct 2026, 08:50 UTC
- https://viperatech.com/news-details/upcoming-eol-notifications-nvidia-h100-nvl-l40-and-a2-models — Status; last verified 11 Oct 2026, 17:10 UTC
- https://images.nvidia.com/aem-dam/Solutions/geforce/ada/nvidia-ada-gpu-architecture.pdf — Memory bandwidth, FP32 compute, FP8 compute, INT8 compute; last verified 11 Oct 2026, 10:29 UTC