NVIDIA · Data Center

nVidia L40

The nVidia L40 is a graphics card released on October 13, 2022, built on the Ada Lovelace architecture. It has a boost clock of 2.49 GHz. It scores 27,355 in the PassMark G3D benchmark. It supports CUDA compute capability 8.9.

Ada Lovelace

5/10 key specs recorded · 30 facts

Depth: 18 recorded fields, 10 features, 5 PassMark workloads

Specification data last verified October 1, 2026 against PassMark Videocard Benchmark, NVIDIA Developer: CUDA GPUs, NVIDIA Developer: Video Encode and Decode GPU Support Matrix and Wikipedia GPU list tables (wikigrid-2026-09). Coverage: 5 of 10 tracked specifications recorded.

PassMark Videocard Benchmark NVIDIA Developer: CUDA GPUs NVIDIA Developer: Video Encode and Decode GPU Support Matrix Wikipedia GPU list tables (wikigrid-2026-09)PassMark Videocard Benchmark

Shading units

n/a

142 SMs

Memory

n/a

GDDR6

Boost clock

2.49 GHz

Board power

n/a

Performance

The nVidia L40 scores 27,355 in the PassMark G3D benchmark, higher than 98.8% of the 2,658 GPUs benchmarked (PassMark rank #35), measured across 2 submitted results. Its PassMark G2D score is 1,186.

PassMark G3D Mark

27,355

Rank #35
Faster than 98.8% of 2,658 GPUs
2 samples

0relative to the fastest GPU on record (41,928)

PassMark workload tests

DirectX 9 398 fps

reference: fastest recorded 526 fps · faster than 99.4% of 1,675 GPUs

DirectX 10 200 fps

reference: fastest recorded 231 fps · faster than 99.2% of 1,602 GPUs

DirectX 11 291 fps

reference: fastest recorded 362 fps · faster than 98.7% of 1,430 GPUs

DirectX 12 63 fps

reference: fastest recorded 213 fps · faster than 86.2% of 1,274 GPUs

GPU Compute 23,067 ops/s

reference: fastest recorded 26,591 ops/s · faster than 99.5% of 1,447 GPUs

Averages of PassMark PerformanceTest submissions; frames/sec are PassMark test-scene rates, not game FPS. Tests PassMark does not report for this card are omitted. PassMark listing

In the PassMark workload tests the nVidia L40 averages DirectX 9 398 fps, DirectX 10 200 fps, DirectX 11 291 fps, DirectX 12 63 fps and GPU Compute 23,067 ops/s, across 2 submitted results. Frames per second are PassMark test-scene rates, not game frame rates.

As stated by PassMark

First benchmarked 2023-07-30

Samples 2

PassMark listing (collected 2026-10-01)

Not to be confused with

This page covers the nVidia L40 specifically. It is a different product from NVIDIA L40-16Q, NVIDIA L40-3Q, NVIDIA L40-6Q, NVIDIA L40-8Q, NVIDIA L40S, NVIDIA L40S-12A, which have their own specifications. Check the exact model name before comparing figures.

Graphics processor

Architecture Ada Lovelace

Codename Not recorded

Chip Not recorded

Process node Not recorded

Transistors Not recorded

Die size Not recorded

The nVidia L40 is based on the Ada Lovelace architecture.

Shader configuration

Shading units Not recorded

Compute units Not recorded

Streaming multiprocessors 142

Execution units Not recorded

Texture units (TMUs) Not recorded

Render output units (ROPs) Not recorded

Ray tracing cores Not recorded

Tensor / AI cores Not recorded

XMX engines Not recorded

Infinity cache Not recorded

The nVidia L40 142 streaming multiprocessors.

The nVidia L40 does not use XMX engines; those are specific to Intel Arc graphics. Infinity Cache is an AMD architectural feature and does not apply to the nVidia L40.

Clock speeds

Base clock Not recorded

Boost clock 2.49 GHz

Game clock Not recorded

Memory clock Not recorded

Effective memory clock Not recorded

The nVidia L40 boosts to 2.49 GHz.

Memory

Size Not recorded

Type GDDR6

Bus width Not recorded

Bandwidth Not recorded

Market

Launched October 13, 2022

Launch price Not recorded

Status Not recorded

Form factor Not recorded

Segment Desktop

Series Data Center

The nVidia L40 was released on October 13, 2022.

Benchmarks

PassMark G3D 27,355

PassMark G2D 1,186

Rank #35

Samples 2

Graphics and compute APIs

The nVidia L40 supports CUDA compute capability 8.9.

CUDA compute capability 8.9

Feex has no recorded Vulkan version for the nVidia L40. Feex has no recorded OpenCL version for the nVidia L40.

Features

The nVidia L40 has 1 supported feature recorded outside the media engine. A feature that no source mentions is shown as not listed, never as unsupported.

Compute and AI

Supported: CUDA Compute capability 8.9

Support for NVIDIA's CUDA computing platform, used by many creative, scientific and AI applications.

Not listed (2)

No source Feex holds states whether the nVidia L40 supports Tensor cores and NVLink / SLI. That is silence, not a statement that they are unsupported.

The nVidia L40 supports CUDA (Compute capability 8.9) under Compute and AI.

Media engine

The nVidia L40 provides hardware encode for H.264 (AVC), HEVC (H.265) and AV1 and hardware decode for H.264 (AVC), HEVC (H.265), AV1 and VP9.

NVIDIA NVENC encoder 8th Generation Encoder engines: 3NVIDIA's dedicated video-encoding engine, used by streaming and capture software; newer generations encode more efficiently.

NVIDIA NVDEC decoder 5th Generation Decoder engines: 3NVIDIA's dedicated video-decoding engine; newer generations support more codecs and formats.

Hardware video codec support of the nVidia L40
Codec	Encode	Decode
H.264 (AVC)	Supported4:4:4: Yes	Supported
HEVC (H.265)	Supported4:2:2: No; 4:4:4: Yes; 10-bit: Yes; B-frames: Yes; 8K: Yes	Supported4:4:4: Yes
AV1	Supported	Supported
VP9	Not stated by the vendor	Supported

supported explicitly not supported not stated by the vendor

Media engines recorded for the nVidia L40: NVIDIA NVENC encoder (8th Generation, encoder engines: 3) and NVIDIA NVDEC decoder (5th Generation, decoder engines: 3).

Frequently asked questions

How fast is the nVidia L40?

The nVidia L40 scores 27,355 in the PassMark G3D benchmark, higher than 98.8% of the 2,658 GPUs benchmarked. Its PassMark rank is #35. In the PassMark DirectX 12 test it averages 63 fps.