GPU Wiki

Compare GPUs

Select up to four GPU Wiki entries to compare matching specifications row by row. The comparison uses the site database and keeps generation-specific specs visibly separate.

Popular comparisons

Add a third or fourth GPU
Spec RTX 4000 SFF Ada Generation
Overview
Product name NVIDIA RTX 4000 SFF Ada Generation
Architecture Ada Lovelace
Generation / family NVIDIA RTX Ada Series
GPU codename AD104
Launch date 2023-03-21
Market segment Workstation, Creator in NVIDIA RTX Ada Series
Board type / entry type Workstation GPU
GPU
Process node TSMC 5 nm
Die size 294 mm²
Transistor count 35.8 billion
GPU chip AD104
SM / multiprocessor count 48
CUDA Cores 6144
Tensor Cores 192
RT Cores 48
ROPs 64
TMUs 192
Clocks
Base / Core clock 720 MHz
Boost clock 1,560 MHz
Memory clock 1,750 MHz
Memory
Memory size 20 GB
Memory type GDDR6
Memory bus width 160-bit
Memory bandwidth 280 GB/s
Bus / Interface
Bus interface PCIe 4.0 x16
AGP / PCI / PCIe distinction PCIe
Power
TDP / TBP / board power 70 W
Recommended PSU 250 W
Power connectors None
Slot width Dual-slot, 168 mm length
Display / Media
Display outputs 4x mini-DisplayPort 1.4a
Features
DirectX support DirectX 12.2
OpenGL support OpenGL 4.6
Vulkan support Vulkan 1.4
CUDA support 8.9
Shader Model 6.8
Ray tracing support Hardware RT units present
Performance / Benchmarks
FP32 throughput 19.17 TFLOPS
FP16 throughput 19.17 TFLOPS
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.

Frame rates compare runs of the same game at the same quality preset on one test system. DLAA counts as native resolution, because it applies anti-aliasing at full render resolution rather than upscaling; DLSS and FSR upscaling are never counted as native. Where a capture named ray tracing without a readable on or off value, it is read as on.