NVIDIA GeForce GTX 1070 Max-Q: specs and benchmarks

NVIDIA GeForce GTX 1070 Max-Q

Summary

NVIDIA started GeForce GTX 1070 Max-Q sales 27 June 2017. This is Pascal architecture notebook card based on 16 nm manufacturing process and primarily aimed at gamers. 8 GB of GDDR5 memory clocked at 8.01 GHz are supplied, and together with 256 Bit memory interface this creates a bandwidth of 256.3 GB / s.

Compatibility-wise, this is card attached via PCIe 3.0 x16 interface. Power consumption is at 115 Watt.

It provides good gaming and benchmark performance at 32.53 percent of a leader's which is NVIDIA Quadro RTX 6000.

General info

Of GeForce GTX 1070 Max-Q's architecture, market type and release date.
Place in performance rating
 
Architecture
Pascal
 
Code name
GP104
 
Type
Laptop
 
Release date
27 June 2017
 

Technical specs

GeForce GTX 1070 Max-Q's general performance parameters such as number of shaders, GPU core clock, manufacturing process, texturing and calculation speed. These parameters indirectly speak of GeForce GTX 1070 Max-Q's performance, but for precise assessment you have to consider its benchmark and gaming test results.
Pipelines
2048
 
Core clock speed
1215 MHz
 
of 1620 (Quadro RTX 5000)
Boost Clock
1379 MHz
 
of 1815 (Quadro RTX 5000)
Transistor count
7,200 million
 
of 21100
Manufacturing process technology
16 nm
 
Power consumption (TDP)
115 Watt
 
of 900 (Tesla S2050)
Texture fill rate
176.5 GTexel / s
 
Floating-point performance
5,648 gflops
 
of 16384 (Radeon Pro Duo)

Compatibility, dimensions and requirements

Information on GeForce GTX 1070 Max-Q's compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For notebook video cards it's notebook size, connection slot and bus, if the video card is inserted into a slot instead of being soldered to the notebook motherboard.
Laptop size
large
 
Interface
PCIe 3.0 x16
 
Supplementary power connectors
None
 

Memory

Parameters of memory installed on GeForce GTX 1070 Max-Q: its type, size, bus, clock and resulting bandwidth. Note that GPUs integrated into processors don't have dedicated memory and use a shared part of system RAM.
Memory type
GDDR5
 
Maximum RAM amount
8 GB
 
Memory bus width
256 Bit
 
of 8192 (Radeon Pro Duo)
Memory clock speed
8008 MHz
 
of 14000
Memory bandwidth
256.3 GB / s
 
of 1024 (Radeon Pro Duo)
Shared memory
-
 

Video outputs and ports

Types and number of video connectors present on GeForce GTX 1070 Max-Q.
Display Connectors
No outputs
 
G-SYNC support
+
 

Technologies

Technological solutions and APIs supported by GeForce GTX 1070 Max-Q. You'll probably need this information if you need some particular technology for your purposes.
VR Ready
+
 
Multi-Projection
+
 
Multi Monitor
+
 

API support

APIs supported by GeForce GTX 1070 Max-Q, sometimes including their particular versions.
DirectX
12.0 (12_1)
 
OpenGL
4.6
 
Vulkan
+
 

Benchmark performance

Non-gaming benchmarks performance of GeForce GTX 1070 Max-Q. Note that overall benchmark performance is measured in points in 0-100 range.

Overall benchmark performance

32.53

3DMark Ice Storm GPU

334256

3DMark Cloud Gate GPU

99552

3DMark Fire Strike Score

12599

3DMark Fire Strike Graphics

14679

3DMark 11 Performance GPU

18688

3DMark Vantage Performance

44090

Passmark

6950

Game benchmarks

Let's see how good GeForce GTX 1070 Max-Q is for gaming. Particular gaming benchmark results are measured in FPS. Comparisons with system requirements are included, but remember that sometimes official requirements may reflect real performance inaccurately.

Relative perfomance

Overall GeForce GTX 1070 Max-Q performance compared to its nearest competitors. All GPU types participate.

AMD equivalent

We believe that the nearest equivalent to GeForce GTX 1070 Max-Q from AMD is Radeon RX Vega M GH, which is nearly equal in speed and higher by 1 position in our rating.

Advices and comments

Here you can ask a question about GeForce GTX 1070 Max-Q, agree or disagree with our judgements, or report an error or mismatch.