NVIDIA · RTX

NVIDIA RTX 4000 SFF Ada Generation

The NVIDIA RTX 4000 SFF Ada Generation is a graphics card released on March 21, 2023, built on the Ada Lovelace architecture. It has 6,144 shading units and a boost clock of 1.56 GHz. It scores 20,558 in the PassMark G3D benchmark. It supports OpenGL 4.6, Vulkan 1.3, OpenCL 3.0 and CUDA compute capability 8.9.

Ada LovelaceAD104

6/10 key specs recorded · 40 facts

Depth: 27 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: 6 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

6,144cores

Memory

n/a

GDDR6

Boost clock

1.56 GHz

720 MHz base

Board power

n/a

Performance

The NVIDIA RTX 4000 SFF Ada Generation scores 20,558 in the PassMark G3D benchmark, higher than 96.9% of the 2,658 GPUs benchmarked (PassMark rank #87), measured across 245 submitted results. Its PassMark G2D score is 1,060.

PassMark G3D Mark

20,558

Rank #87
Faster than 96.9% of 2,658 GPUs
245 samples

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

PassMark workload tests

DirectX 9 271 fps

reference: fastest recorded 526 fps · faster than 96.2% of 1,675 GPUs

DirectX 10 108 fps

reference: fastest recorded 231 fps · faster than 91.8% of 1,602 GPUs

DirectX 11 169 fps

reference: fastest recorded 362 fps · faster than 92.7% of 1,430 GPUs

DirectX 12 84 fps

reference: fastest recorded 213 fps · faster than 93.6% of 1,274 GPUs

GPU Compute 9,522 ops/s

reference: fastest recorded 26,591 ops/s · faster than 93.8% 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 RTX 4000 SFF Ada Generation averages DirectX 9 271 fps, DirectX 10 108 fps, DirectX 11 169 fps, DirectX 12 84 fps and GPU Compute 9,522 ops/s, across 245 submitted results. Frames per second are PassMark test-scene rates, not game frame rates.

Theoretical throughput

FP32 (single precision) 19.169 TFLOPS calculatedcalculated from shaders x boost clock (MHz) x 2 / 1e6 = 6144 x 1560 x 2 / 1e6

FP32 (single precision) (19.169 TFLOPS) is calculated by Feex from stored specifications, not stated by NVIDIA.

As stated by PassMark

First benchmarked 2023-04-21

Samples 245

PassMark listing (collected 2026-10-01)

Graphics processor

Architecture Ada Lovelace

Codename AD104

Chip Not recorded

Process node Not recorded

Transistors Not recorded

Die size Not recorded

The NVIDIA RTX 4000 SFF Ada Generation is based on the Ada Lovelace architecture and uses the AD104 graphics processor.

Shader configuration

Shading units 6,144

Compute units Not recorded

Streaming multiprocessors Not recorded

Execution units Not recorded

Texture units (TMUs) 192

Render output units (ROPs) 80

Ray tracing cores Not recorded

Tensor / AI cores Not recorded

XMX engines Not recorded

Infinity cache Not recorded

The NVIDIA RTX 4000 SFF Ada Generation has 6,144 shading units, 192 texture mapping units and 80 render output units.

The NVIDIA RTX 4000 SFF Ada Generation 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 RTX 4000 SFF Ada Generation. Feex has no recorded ray tracing core count for the NVIDIA RTX 4000 SFF Ada Generation.

Clock speeds

Base clock 720 MHz

Boost clock 1.56 GHz

Game clock Not recorded

Memory clock Not recorded

Effective memory clock Not recorded

The NVIDIA RTX 4000 SFF Ada Generation runs at a base clock of 720 MHz and boosts to 1.56 GHz.

Memory

Size Not recorded

Type GDDR6

Bus width Not recorded

Bandwidth Not recorded

Market

Launched March 21, 2023

Launch price $1,250

Status Not recorded

Form factor Not recorded

Segment Desktop

Series RTX

The NVIDIA RTX 4000 SFF Ada Generation was released on March 21, 2023 and launched at a price of $1,250.

Benchmarks

PassMark G3D 20,558

PassMark G2D 1,060

Rank #87

Samples 245

Graphics and compute APIs

The NVIDIA RTX 4000 SFF Ada Generation supports OpenGL 4.6, Vulkan 1.3, OpenCL 3.0 and CUDA compute capability 8.9.

OpenGL 4.6

Vulkan 1.3

OpenCL 3.0

CUDA compute capability 8.9

Features

The NVIDIA RTX 4000 SFF Ada Generation 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 RTX 4000 SFF Ada Generation supports Tensor cores and NVLink / SLI. That is silence, not a statement that they are unsupported.

The NVIDIA RTX 4000 SFF Ada Generation supports CUDA (Compute capability 8.9) under Compute and AI.

Media engine

The NVIDIA RTX 4000 SFF Ada Generation 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: 2NVIDIA's dedicated video-encoding engine, used by streaming and capture software; newer generations encode more efficiently.

NVIDIA NVDEC decoder 5th Generation Decoder engines: 2NVIDIA's dedicated video-decoding engine; newer generations support more codecs and formats.

Hardware video codec support of the NVIDIA RTX 4000 SFF Ada Generation
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 RTX 4000 SFF Ada Generation: NVIDIA NVENC encoder (8th Generation, encoder engines: 2) and NVIDIA NVDEC decoder (5th Generation, decoder engines: 2).

Frequently asked questions

How fast is the NVIDIA RTX 4000 SFF Ada Generation?

The NVIDIA RTX 4000 SFF Ada Generation scores 20,558 in the PassMark G3D benchmark, higher than 96.9% of the 2,658 GPUs benchmarked. Its PassMark rank is #87. In the PassMark DirectX 12 test it averages 84 fps.

Does the NVIDIA RTX 4000 SFF Ada Generation support AV1 encoding?

Yes. The NVIDIA RTX 4000 SFF Ada Generation supports AV1 hardware encoding and AV1 hardware decoding.

What is the CUDA compute capability of the NVIDIA RTX 4000 SFF Ada Generation?

The NVIDIA RTX 4000 SFF Ada Generation has CUDA compute capability 8.9.

When was the NVIDIA RTX 4000 SFF Ada Generation released and how much did it cost at launch?

The NVIDIA RTX 4000 SFF Ada Generation was released on March 21, 2023 and launched at a price of $1,250.

Corrections to this record

After an audit, 1 empty field was filled from sources. Each change is listed with its old value, new value, rule and sources.

1 filled value

Architecture: Ada Lovelace (was Not recorded). Rule: Architecture from chip codename. chip AD104 -> Ada Lovelace. Sources: Wikipedia: List of Nvidia graphics processing units (revision 1377107724).

The audit log is public: all changes for this GPU, the corrections overview and the method.