NVIDIA GPU-Vergleich

Hier finden Sie eine Übersicht aller aktuellen NVIDIA GPUs. Anhand der Tabellen können Sie die verschiedenen GPU-Modelle direkt vergleichen, um die bestmögliche Lösung zu finden.
Weitere Informationen oder Einzelpreise können Sie unter dem jeweiligen Link des Produktes erhalten.

       
 New NVIDIA Data Center GPUs
 
 B200B100H200H100
L40S
L40
L4
DesignHighest Perf AI, HPC, DAHighest Perf AI, HPC, DAHighest Perf AI, HPC, DAMainstream, Training and HPHighest Perf UniversalPowerful Graphics + AIPowerful Graphics + AI
Form Factor
SXM5SXM5SXM5SXM5PCIe Gen5 x16 2 Slot FHFL 3 NVLink BridgeNVL 2x PCIe Gen5 x16 2x 2 Slot FHFL NVLink BridgedPCIe Gen4 x16 2 Slot FHFL
PCIe Gen4 x16 2 Slot FHFL
PCIe Gen4 x16 1 Slot HHHL
Max Power1200W | 1000W700W700W700W350W2x 400W350W300W72W
FP64 TC | FP32 TFLOPS40 | 80 (no-sparse)30 | 60 (no-sparse)67 | 67
67 | 67
51 | 51
134 | 134
NA | 91.6
NA | 90
NA | 30.3
TF32 TC | FP16 TC TFLOPS
2200 | 45001800 | 3500
989 | 1979
989 | 1979
756 | 1513
1979 | 3958
366 | 733
181 | 362
120 | 242
FP8/FP6 TC | INT8 TC TFLOPS/TOPS
9000 | 90007000 | 70003958 | 39583958 | 39583026 | 3026
7916 | 7916
1466 | 1466724 | 724485 | 485
FP4 TC
1800014000-------
GPU Memory
Up to 192 GB
Up to 8000 GB/s
Up to 192 GB
Up to 8000 GB/s
141 GB HBM3e 4800GB/s
80 GB HBM3 3350GB/s
80 GB HBM2e 2000GB/s
188 GB HBM2e 7800GB/s
48 GB GDDR6 864GB/s
48 GB GDDR6 864GB/s
24 GB GDDR6 300GB/s
Multi-Instance GPU (MIG)
Up to 7Up to 7Up to 7Up to 7Up to 7Up to 14
---
NVLink Connectivity
Up to 256Up to 256Up to 256Up to 2562 cards2 cards
---
Media Acceleration
7 JPEG Decoder
7 Video Decoder
7 JPEG Decoder
7 Video Decoder
7 JPEG Decoder
7 Video Decoder
7 JPEG Decoder
7 Video Decoder
7 JPEG Decoder
7 Video Decoder
14 JPEG Decoder
14 Video Decoder
3 Video Encoder
3 Video Decoder
4 JPEG Decoder
3 Video Encoder
3 Video Decoder
4 JPEG Decoder
2 Video Encoder
4 Video Decoder
4 JPEG Decoder
Ray Tracing
------YesYesYes
Transformer Engine
YesYesYesYesYesYesYesYesYes
DPX Instructions
??YesYesYesYes---
Graphics
(no vPC or RTX vWS)(no vPC or RTX vWS)(no vPC or RTX vWS)(no vPC or RTX vWS)(no vPC or RTX vWS)(no vPC or RTX vWS)Top-of-LineTop-of-Line(NVIDIA vWS /vPC (Entry-Mid)
vGPU
YesYesYesYesYesYesYesYesYes
Hardware Root of Trust
Internal and ExternalInternal and ExternalInternal and ExternalInternal and ExternalInternal and ExternalInternal and ExternalInternal and ExternalInternal
-
Confidential Computing
YesYesYesYesYesYes---
NVIDIA AI Enterprise
Add-onAdd-onAdd-onAdd-onIncludedIncludedAdd-onAdd-onAdd-on
 InfoInfoInfoInfoPreisPreisPreisPreisPreis
     Edu/StartupEdu/StartupEdu/StartupEdu/Startup 
     
 Last NVIDIA Data Center GPUs
 A100/A800A30A40
A10
A16
A2
DesignHighest Perf ComputeMainstream Compute
High Perf Graphics
Mainstream & Video with AI
High Density Virtual Desktop
Entry-Level Small Footprint
Form Factor
SXM4PCIe Gen4 x16 2 Slot FHFL 3 NVLink Bridge
PCIe Gen4 x16 2 Slot FHFL 1 NVLink Bridge
PCIe Gen4 x16 2 Slot FHFL 1 NVLink BridgePCIe Gen4 x16 1 Slot FHFLPCIe Gen4 x16 2 Slot FHFLPCIe Gen4 x8 1 Slot LP
Max Power500W300W165W300W150W250W60W
FP64 TC | FP32 TFLOPS19.5 | 19.5
19.5 | 19.5
10 | 10
NA | 37
NA | 31
NA | 4x 4.5
NA | 4.5
TF32 TC | FP16 TC TFLOPS
312 | 624312 | 624165 | 330
150 | 300
125 | 250
4x 18 | 4x 36
18 | 36
FP8/FP6 TC | INT8 TC TFLOPS/TOPS
NA | 1248NA | 1248NA | 661NA | 600NA | 500NA | 4x 72
NA | 72
FP4 TC
-------
GPU Memory
80 GB HBM2e
80 GB HBM2e
24 GB HBM2
48 GB GDDR6
24 GB GDDR6
4x 16 GB GDDR6
16 GB GDDR6
Multi-Instance GPU (MIG)
Up to 7Up to 7Up to 4----
NVLink Connectivity
Up to 8
2 cards
2 cards
2 cards
-
-
-
Media Acceleration
1 JPEG Decoder
5 Video Decoder
1 JPEG Decoder
5 Video Decoder
1 JPEG Decoder
4 Video Decoder
1 Video Encoder
2 Video Decoder
(+AV1 decode)
1 Video Encoder
2 Video Decoder
(+AV1 decode)
4 Video Encoder
8 Video Decoder
(+AV1 decode)
1 Video Encoder
2 Video Decoder
(+AV1 decode)
Ray Tracing
---YesYesYesYes
Transformer Engine
-------
DPX Instructions
-------
Graphics
For-in-situ viz
(no vPC or RTX vWS)
For-in-situ viz
(no vPC or RTX vWS)
For-in-situ viz
(no vPC or RTX vWS)
BestBetterGoodGood
vGPU
YesYesYesYesYesYesYes
Hardware Root of Trust
Internal with Option for External
Internal with Option for External
Internal with Option for External
Internal with Option for External
Internal with Option for External
Internal with Option for External
Internal with Option for External
Confidential Computing
(1)------
NVIDIA AI Enterprise
Add-onAdd-onAdd-onAdd-onAdd-onAdd-onAdd-on
   PreisPreis PreisPreis
     
  NVIDIA RTX Desktop GPUs
 RTX A400
RTX A1000
RTX 2000 Ada
RTX 4000 Ada
RTX 4500 Ada
RTX 5000 Ada
RTX 6000 Ada
GPU Architecture
AmpereAmpereAda-Lovelace
Ada-Lovelace
Ada-Lovelace
Ada-Lovelace
Ada-Lovelace
CUDA Cores
76823042816614476801280018176
Tensor Cores
24 (3. Gen)
72 (3. Gen)
88 (4. Gen)
192 (4. Gen)
240 (4. Gen)
400 (4. Gen)
568 (4. Gen)
RT Cores
6 (2. Gen)
18 (2. Gen)
22 (3. Gen)
48 (3. Gen)
60  (3. Gen)
100  (3. Gen)
142 (3. Gen)
Peak Single-Precision Performance
2.7 TFLOPS
6.7 TFLOPS
12 TFLOPS
26.7 TFLOPS
39.6 TFLOPS
65.3 TFLOPS
91.1 TFLOPS
Peak Double-Precision Performance
-------
Tensor Performance
21.7 TFLOPS
53.8 TFLOPS
191.9 TFLOPS
327.6 TFLOPS
634.0 TFLOPS
1044.4 TFLOPS
1457.0 TFLOPS
RT Core Performance
5.4 TFLOPS
13.2 TFLOPS
27.7 TFLOPS
61.8 TFLOPS
91.6 TFLOPS
151.0 TFLOPS
210.6 TFLOPS
Memory Size
4 GB
8 GB
16 GB GDDR6
20 GB GDDR6
24 GB GDDR6
32 GB GDDR6
48 GB GDDR6
Memory Bandwidth
96 GB/s
192 GB/s
224 GB/s
360 GB/s
432 GB/s
576 GB/s
960 GB/s
NVLink
Not supported
Not supported
Not supported
Not supported
Not supported
Not supported
Not supported
VR Ready
NoNoYesYesYesYesYes
Virtual Workstation
NoNoNoNoNoYesYes
Display Connectors
4x mDP 1.4a4x mDP 1.4a4x mDP 1.4a4x DP 1.4a4x DP 1.4a4x DP 1.4a4x DP 1.4a
Form Factor
2.7"H x 6.4"L, Single Slot
2.7"H x 6.4"L, Single Slot
2.7"H x 6.4"L, Single Slot
4.4"H x 9.5"L, Single Slot
4.4"H x 10.5"L, Dual Slot
4.4"H x 10.5"L, Dual Slot
4.4"H x 10.5"L, Dual Slot
Max Power Consumption
50 W50 W70 W130 W210 W250 W300 W
Graphics Bus
PCIe Gen 4 x8 *
PCIe Gen 4 x8 *
PCIe Gen 4 x8 *
PCIe Gen 4 x16
PCIe Gen 4 x16
PCIe Gen 4 x16
PCIe Gen 4 x16
   PreisPreisPreis PreisPreis
      Edu/StartupEdu/Startup

 

Haben Sie Fragen zu den NVIDIA GPU Modellen, helfen oder geben wir Ihnen dazu gerne eine Auskunft. 

Kontakt:   
Tel: +49 40 300672 - 0    |   Fax: +49 40 300672 - 11   |   E-Mail: info[at]delta.de