NVIDIA GeForce RTX 3060 Max-Q vs NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce RTX 3050 Ti Laptop GPU
NVIDIA GeForce RTX 3060 Max-Q► remove from comparison
The Nvidia GeForce RTX 3060 Max-Q (for laptops, GN20-E3, Max-Q) is the former name for a RTX 3060 Laptop GPU with Max-Q technologies. In previous generations, the Max-Q name was used for low power versions. With the RTX 3000 series, every TGP-version can now use Max-Q technologies and all GPUs are called RTX 3060 Laptop GPU (60 - 115W).
NVIDIA GeForce RTX 3090 Ti► remove from comparison
The Nvidia GeForce RTX 3090 Ti is a high-end desktop graphics card based on the Ampere generation. It was announced early 2022 the fastest desktop gaming graphics card.
It uses the big GA102 chip and offers 10,752 shaders and 24 GB GDDR6X graphics memory. The RTX3090ti is rated at 450 Watt.
NVIDIA GeForce RTX 3050 Ti Laptop GPU► remove from comparison
The Nvidia GeForce RTX 3050 Ti Laptop GPU (for laptops, NVIDIA_DEV.2583, GN20-P1) is a faster variant of the RTX 3050 mobile card and based on the GA107 Ampere chip. The chip offers 2560 CUDA, 20 Ray Tracing and 80 Tensor cores. The clock rate depends on the used TGP-version (from 35 - 80 Watt).
|TGP (Power Consumption)||35 W||40 W||45 W||50 W||60 W||70 W||80 W|
|Base Clock Speed (MHz)||735||915||1043||1140||1223||1350||1463|
|Boost Clock Speed (MHz)||1035||1185||1290||1410||1485||1598||1695|
The performance (of the high TGP variants) should be similar to the old RTX 2060 and therefore most suited for 1080p gaming with high detail settings. The performance is not sufficient to enable Raytracing in most games, but the Tensor cores can be used for DLSS in some games (and get a performance boost with a slight quality reduction). Beware, that the low TGP variants will offer a significantly lower performance.
The GA107 chip offers 3,072 FP32 ALUs of which half can also execute INT32 instructions (i.e. 1,536 INT32 ALUs). The RTX 3050 Ti however maybe won't use all ALUs on the chip. With Turing all shaders could still execute FP32 or INT32 instructions. The raytracing and tensor cores on the chip were also improved according to Nvidia. The Ampere chips also include an improved 5th generation video encoder (NVENC for H.264 and H.265) and a 7th generation decoder (for various formats now including AV1).
The GA107 chip is manufactured by Samsung in 8nm (8N), which is not quite able to keep up with the 7nm node at TSMC (e.g. used by AMD and also for the professional GA100 Ampere chip).
|NVIDIA GeForce RTX 3060 Max-Q||NVIDIA GeForce RTX 3090 Ti||NVIDIA GeForce RTX 3050 Ti Laptop GPU|
|GeForce RTX 3000 Series|
|Codename||GN20-E3 GA106||Ampere GA102||GN20-P1|
|Pipelines||3840 - unified||10752 - unified||2560 - unified|
|Core Speed||1283 (Boost) MHz||1560 - 1860 (Boost) MHz||1222 - 1485 (Boost) MHz|
|Memory Bus Width||192 Bit||384 Bit||128 Bit|
|Max. Amount of Memory||6 GB||24 GB||4 GB|
|API||DirectX 12_2, Shader 7.0, OpenGL 4.6||DirectX 12_2, Shader 7.0, OpenGL 4.6||DirectX 12_2, Shader 7.0, OpenGL 4.6|
|Power Consumption||60 Watt||450 Watt||60 Watt (35 - 80 Watt TGP)|
|technology||8 nm||8 nm||8 nm|
|Date of Announcement||04.01.2021||27.01.2022||10.05.2021|
|Tensor / AI Cores||336||80|
|Theoretical Performance||40 TFLOPS FP16, 40 TFLOPS FP32, 625 TFLOPS FP64|
|Cache||L1: 10.5 MB, L2: 6 MB|
|Memory Speed||21000 effective = 1313 MHz||12000 effective = 1500 MHz|
|Memory Bandwidth||1008 GB/s||195 GB/s|
|Die Size||628 mm²|
|Displays||4 Displays (max.), HDMI 2.1, DisplayPort 1.4a||HDMI 2.1, DisplayPort 1.4a|
|Predecessor||GeForce RTX 2080 Ti (Desktop)|
|Features||NVIDIA DLSS, NVIDIA Reflex, NVIDIA Broadcast, Resizable BAR, NVIDIA Ansel, NVIDIA FreeStyle, NVIDIA ShadowPlay®, NVIDIA G-SYNC®|