NVIDIA GeForce RTX 3060 Max-Q vs NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce RTX 3080 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 3080 Laptop GPU► remove from comparison
The Nvidia GeForce RTX 3080 Laptop GPU or 3080 Mobile (for laptops, GN20-E7) is the fastest graphics card for notebooks in early 2021. It is based on the GA104-775-A1 Ampere chip and offers 8 or 16 GB GDDR6 graphics memory with a 256 Bit memory bus. It supports PCIe 4.0 and will be available in different variants from 80 - 150 Watt (TGP) (80, 90, 115, 125, 135, 145 and 150+ Watt). As package the notebook graphic card uses GB5-256 and the chip size is 40x40mm. The GPU supports eDP 1.4b to connect the internal monitor.
There is no more Max-Q variant (formerly used for the low power variants) but every OEM can choose to implement Max-Q technologies (Dynamic Boost, Whispermode).
The performance depends on the TGP setting and cooling of the laptop. At the same TGP level the RTX3080 should be faster than the old top model, the RTX 2080 Super Mobile and similar to the desktop RTX 3070. This means, the GPU should be well suited for 4k gaming or QHD with high frame rates. The similar named RTX 3080 desktop card is significantly faster.
The GA104 chip offers 6,144 FP32 ALUs of which half can also execute INT32 instructions (i.e. 3,072 INT32 ALUs). 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 GA104 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 3080 Laptop GPU|
|GeForce RTX 3000 Series|
|Codename||GN20-E3 GA106||Ampere GA102||GN20-E7 GA104|
|Pipelines||3840 - unified||10752 - unified||6144 - unified|
|Core Speed||1283 (Boost) MHz||1560 - 1860 (Boost) MHz||780 - 1100 - 1245 - 1710 (Boost) MHz|
|Memory Bus Width||192 Bit||384 Bit||256 Bit|
|Max. Amount of Memory||6 GB||24 GB||16 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||150 Watt (80 - 150 Watt TGP)|
|technology||8 nm||8 nm||8 nm|
|Date of Announcement||04.01.2021||27.01.2022||12.01.2021|
|Tensor / AI Cores||336|
|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||14000 effective = 1750 MHz|
|Memory Bandwidth||1008 GB/s||448 GB/s|
|Transistors||28.3 Billion||17.4 Billion|
|Die Size||628 mm²||392 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, Resizable BAR, NVIDIA Broadcast, NVIDIA Ansel, NVIDIA ShadowPlay®, NVIDIA G-SYNC®, Advanced Optimus, Nvidia Max-Q, Dynamic Boost, VR-ready, Nvidia Omniverse|