# L4

> NVIDIA · Ada Lovelace

Canonical: https://gpuninja.com/chips/l4
Data as of: 2026-10-11T10:29:24Z
Path: Home › GPU chips
- Specs verified: between 11 Oct 2026, 08:50 UTC and 11 Oct 2026, 10:29 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: AD104 (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: 7,424 (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Tensor cores: 232 (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- RT cores: 58 (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Memory bus: 192-bit (Verified · source nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Max VRAM: 24 GB (Verified · source nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Reference boost clock: 2,040 MHz (Verified · source nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)
- Reference TDP: 72 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 nvidia.com · retrieved 11 Oct 2026, 09:50 UTC · checked 11 Oct 2026, 10:29 UTC)
- Launch MSRP: No public MSRP
- Launch date: 21 Mar 2023 (Verified · source investor.nvidia.com · retrieved 11 Oct 2026, 07:12 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:27b8 (Verified · source download.nvidia.com · retrieved 11 Oct 2026, 07:01 UTC · checked 11 Oct 2026, 08:50 UTC)
- Status: Active (Verified · source nvidia.com · retrieved 11 Oct 2026, 07:02 UTC · checked 11 Oct 2026, 08:50 UTC)

## Performance

- Memory bandwidth: 300 GB/s (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 09:47 UTC · checked 11 Oct 2026, 10:29 UTC)
- FP32 compute: 30.3 TFLOPS (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 09:47 UTC · checked 11 Oct 2026, 10:29 UTC)
- FP16 compute: 121 TFLOPS (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 09:47 UTC · checked 11 Oct 2026, 10:29 UTC)
- BF16 compute: 121 TFLOPS (Verified · source images.nvidia.com · retrieved 11 Oct 2026, 09:47 UTC · checked 11 Oct 2026, 10:29 UTC)
- FP8 compute: 242 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: 242 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/l4/ — Vendor, Architecture, Host interface, Segment, Status; last verified 11 Oct 2026, 10:29 UTC
- https://pci-ids.ucw.cz/read/PC/10de/27b8 — 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/l4/PB-11316-001_v01.pdf — Memory bus, Max VRAM, Reference boost clock, Reference TDP; last verified 11 Oct 2026, 08:50 UTC
- https://investor.nvidia.com/news/press-release-details/2023/NVIDIA-Launches-Inference-Platforms-for-Large-Language-Models-and-Generative-AI-Workloads/default.aspx — 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://images.nvidia.com/aem-dam/Solutions/geforce/ada/nvidia-ada-gpu-architecture.pdf — Memory bandwidth, FP32 compute, FP16 compute, BF16 compute, FP8 compute, INT8 compute; last verified 11 Oct 2026, 10:29 UTC