Home NVIDIA GeForce RTX 3070 Max Q

NVIDIA GeForce RTX 3070 Max Q

This is a GPU manufactured with Samsung 8nm process, based on Nvidia Ampere architecture and released on Jan 2021. It features 17.4 billion transistors, 5120 CUDA cores and 8GB GDDR6 memory, with 4MB L2 cache, theoretical performance of 13.21TFLOPS, with total power consumption of 80W.

Graphics Card

[Report Issues]
Release Date
Jan 2021
Generation
GeForce 30 Mobile
Type
Mobile
Bus Interface
PCIe 4.0 x16

Clock Speeds

[Report Issues]
Base Clock
780MHz
Boost Clock
1290MHz
Memory Clock
1500MHz

Memory

[Report Issues]
Memory Size
8GB
Memory Type
GDDR6
Memory Bus
256bit
Bandwidth
384.0 GB/s

Render Config

[Report Issues]
SM Count
40
Shading Units
5120
TMUs
160
ROPs
80
Tensor Cores
160
RT Cores
40
L1 Cache
128 KB (per SM)
L2 Cache
4MB

Theoretical Performance

[Report Issues]
Pixel Rate
103.2 GPixel/s
Texture Rate
206.4 GTexel/s
FP16 (half)
13.21 TFLOPS
FP32 (float)
13.21 TFLOPS
FP64 (double)
206.4 GFLOPS

Graphics Processor

[Report Issues]
GPU Name
GA104
GPU Variant
GA104-770-A1
Architecture
Ampere
Foundry
Samsung
Process Size
8 nm
Transistors
17,400 million
Die Size
392mm²

Board Design

[Report Issues]
TDP
80W
Outputs
No outputs
Power Connectors
None

Graphics Features

[Report Issues]
DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
8.6
Shader Model
6.6

Rankings

[Report Issues]
FP32 (float)
13.41 TFLOPS
13.41 TFLOPS
13.31 TFLOPS
13.21 TFLOPS
13.21 TFLOPS
13.21 TFLOPS
13.21 TFLOPS

Related Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy