Home NVIDIA GeForce RTX 4070 Max-Q

NVIDIA GeForce RTX 4070 Max-Q

This is a GPU manufactured with TSMC 4nm process, based on Nvidia Ada Lovelace architecture and released on Jan 2023. It features 4608 CUDA cores and 8GB GDDR6 memory, with 32MB L2 cache, theoretical performance of 11.34TFLOPS, with total power consumption of 35W.

Graphics Card

[Report Issues]
Release Date
Jan 2023
Generation
GeForce 40 Mobile
Type
Mobile
Bus Interface
PCIe 4.0 x16

Clock Speeds

[Report Issues]
Base Clock
735MHz
Boost Clock
1230MHz
Memory Clock
1750MHz

Memory

[Report Issues]
Memory Size
8GB
Memory Type
GDDR6
Memory Bus
128bit
Bandwidth
224.0 GB/s

Render Config

[Report Issues]
SM Count
36
Shading Units
4608
TMUs
144
ROPs
48
Tensor Cores
144
RT Cores
36
L1 Cache
128 KB (per SM)
L2 Cache
32MB

Theoretical Performance

[Report Issues]
Pixel Rate
59.04 GPixel/s
Texture Rate
177.1 GTexel/s
FP16 (half)
11.34 TFLOPS
FP32 (float)
11.34 TFLOPS
FP64 (double)
177.1 GFLOPS

Graphics Processor

[Report Issues]
GPU Name
AD106
GPU Variant
GN21-X6
Architecture
Ada Lovelace
Foundry
TSMC
Process Size
4 nm
Transistors
Unknown
Die Size
190mm²

Board Design

[Report Issues]
TDP
35W
Outputs
Portable Device Dependent
Power Connectors
None

Graphics Features

[Report Issues]
DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
8.9
Shader Model
6.7

Rankings

[Report Issues]
FP32 (float)
11.75 TFLOPS
11.61 TFLOPS
NVIDIA Tesla P10 24 GB GDDR5X
11.47 TFLOPS
11.34 TFLOPS
11.34 TFLOPS
AMD Radeon RX 6700 10 GB GDDR6
11.29 TFLOPS
11.29 TFLOPS

Related Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy