Notebookcheck Logo

NVIDIA GeForce RTX 3090 Ti

NVIDIA NVIDIA GeForce RTX 3090 Ti

Die Nvidia GeForce RTX 3090 Ti is zum Launch Anfang 2022 die schnellste GeForce Grafikkarte der Ampere-Generation. Sie nutzt den großen GA102-Chip mit 10.752 Shader und 24 GB GDDR6X Grafikspeicher.

Mit einer Leistungsaufnahme von 450 Watt braucht die GPU zwar sehr viel Strom unter Last, die Energieeffizienz ist jedoch trotzdem sehr gut (Leistung pro Watt).

GeForce RTX 3000 Serie

NVIDIA GeForce RTX 3090 Ti 10752 @ 1.56 - 1.86 GHz384 Bit @ 21000 MHz
NVIDIA GeForce RTX 3090 compare 10496 @ 1.4 - 1.7 GHz384 Bit @ 19500 MHz
NVIDIA GeForce RTX 3080 Ti compare 10240 @ 1.37 - 1.67 GHz384 Bit @ 19000 MHz
NVIDIA GeForce RTX 3080 12 GB compare 8960/ cores @ 1.26 - 1.71 GHz384 Bit @ 19000 MHz
NVIDIA GeForce RTX 3080 compare 8704 @ 1.45 - 1.71 GHz320 Bit @ 19000 MHz
GeForce RTX 3070 Ti compare 6144 @ 1.58 - 1.77 GHz256 Bit @ 19000 MHz
GeForce RTX 3080 Ti Laptop GPU compare 7424 @ 0.98 - 1.59 GHz256 Bit @ 14000 MHz
NVIDIA GeForce RTX 3070 compare 5888 @ 1.5 - 1.73 GHz256 Bit @ 14000 MHz
GeForce RTX 3080 Laptop GPU compare 6144 @ 0.78 - 1.25 GHz256 Bit @ 14000 MHz
NVIDIA GeForce RTX 3060 Ti compare 4864 @ 1.41 - 1.67 GHz256 Bit @ 14000 MHz
GeForce RTX 3070 Ti Laptop GPU compare 5888 @ 0.92 - 1.48 GHz256 Bit @ 14000 MHz
GeForce RTX 3070 Laptop GPU compare 5120 @ 0.78 - 1.29 GHz256 Bit @ 14000 MHz
GeForce RTX 3080 Max-Q compare 6144 @ 0.78 - 1.25 GHz256 Bit @ 6000 MHz
NVIDIA GeForce RTX 3060 compare 3584 @ 1.32 - 1.78 GHz192 Bit @ 15000 MHz
GeForce RTX 3070 Max-Q compare 5120 @ 1.29 GHz256 Bit
GeForce RTX 3060 Laptop GPU compare 3840 @ 0.82 - 1.7 GHz192 Bit @ 14000 MHz
GeForce RTX 3060 Max-Q compare 3840 @ 1.28 GHz192 Bit
NVIDIA GeForce RTX 3050 compare 2560 @ 1.55 - 1.78 GHz128 Bit Bit @ 1750 MHz
GeForce RTX 3050 Ti Laptop GPU compare 2560 @ 1.22 - 1.49 GHz128 Bit @ 12000 MHz
GeForce RTX 3050 6GB Laptop GPU compare 2560 @ 1.24 - 1.49 GHz96 Bit @ 12000 MHz
GeForce RTX 3050 4GB Laptop GPU compare 2048 @ 1.24 - 1.5 GHz128 Bit @ 12000 MHz
CodenameAmpere GA102
ArchitekturAmpere
Pipelines10752 - unified
TMUs336
ROPs112
Raytracing Cores84
Tensor / AI Cores336
Kerntakt1560 - 1860 (Boost) MHz
Theoretical Performance40 TFLOPS FP16, 40 TFLOPS FP32, 625 TFLOPS FP64
CacheL1: 10.5 MB, L2: 6 MB
Speichertakt21000 effective = 1313 MHz
Speicherbandbreite384 Bit
SpeichertypGDDR6X
Max. Speichergröße24 GB
Shared Memorynein
Memory Bandwidth1008 GB/s
APIDirectX 12_2, Shader 6.7, OpenGL 4.6
Stromverbrauch450 Watt
Transistoren28.3 Billion
Chipgröße 628 mm²
Herstellungsprozess8 nm
PCIe4.0 x16
Displays4 Displays (max.), HDMI 2.1, DisplayPort 1.4a
Erscheinungsdatum27.01.2022
PredecessorGeForce RTX 2080 Ti (Desktop)

Benchmarks

Performance Rating - 3DMark 11 + Fire Strike + Time Spy
24.2 pt (73%)
SPECviewperf 12
specvp12 sw-03 +
specvp12 snx-02 +
specvp12 showcase-01 +
specvp12 mediacal-01 +
specvp12 maya-04 +
specvp12 energy-01 +
specvp12 creo-01 +
specvp12 catia-04 +
specvp12 3dsmax-05 +
SPECviewperf 13 specvp13 sw-04 +
specvp13 snx-03 +
specvp13 showcase-02 +
specvp13 medical-02 +
specvp13 maya-05 +
specvp13 energy-02 +
specvp13 creo-02 +
specvp13 catia-05 +
specvp13 3dsmax-06 +
SPECviewperf 2020 specvp2020 solidworks-05 4k +
specvp2020 snx-04 4k +
specvp2020 medical-03 4k +
specvp2020 maya-06 4k +
specvp2020 energy-03 4k +
specvp2020 creo-03 4k +
specvp2020 catia-06 4k +