NVIDIA · GeForce GTX 10 Series

NVIDIA GeForce GTX 1070

The NVIDIA GeForce GTX 1070 is a graphics card released on August 16, 2016, built on the Pascal architecture using a 16 nm process. It has 1,920 shading units, 8 GB of GDDR5 memory on a 256-bit bus, 256.3 GB/s of memory bandwidth, a boost clock of 1.68 GHz and a 150 W board power rating. It scores 13,513 in the PassMark G3D benchmark. It supports DirectX 12, OpenGL 4.6, Vulkan 1.4 and CUDA compute capability 6.1.

PascalGP104-200-A116 nm

10/10 key specs recorded · 74 facts

Depth: 46 recorded fields, 10 features, 5 PassMark workloads

Specification data last verified October 1, 2026 against PassMark Videocard Benchmark, NanoReview (Firecrawl extract), NVIDIA Developer: Video Encode and Decode GPU Support Matrix and Wikipedia GPU list tables (wikigrid-2026-09). Coverage: 10 of 10 tracked specifications recorded.

PassMark Videocard Benchmark NanoReview (Firecrawl extract)PassMark Videocard Benchmark NVIDIA Developer: Video Encode and Decode GPU Support Matrix Wikipedia GPU list tables (wikigrid-2026-09)

Shading units

1,920cores

15 SMs

Memory

8 GB

GDDR5 · 256-bit

Boost clock

1.68 GHz

1.51 GHz base

Board power

150 W

Performance

The NVIDIA GeForce GTX 1070 scores 13,513 in the PassMark G3D benchmark, higher than 92.4% of the 2,658 GPUs benchmarked (PassMark rank #213), measured across 54,233 submitted results. Its PassMark G2D score is 848.

PassMark G3D Mark

13,513

Rank #213
Faster than 92.4% of 2,658 GPUs
54,233 samples

0relative to the fastest GPU on record (41,928)

PassMark workload tests

DirectX 9 198 fps

reference: fastest recorded 526 fps · faster than 90.4% of 1,675 GPUs

DirectX 10 80 fps

reference: fastest recorded 231 fps · faster than 86.5% of 1,602 GPUs

DirectX 11 99 fps

reference: fastest recorded 362 fps · faster than 84.3% of 1,430 GPUs

DirectX 12 49 fps

reference: fastest recorded 213 fps · faster than 79.6% of 1,274 GPUs

GPU Compute 6,122 ops/s

reference: fastest recorded 26,591 ops/s · faster than 87% of 1,447 GPUs

Averages of PassMark PerformanceTest submissions; frames/sec are PassMark test-scene rates, not game FPS. Tests PassMark does not report for this card are omitted. PassMark listing

In the PassMark workload tests the NVIDIA GeForce GTX 1070 averages DirectX 9 198 fps, DirectX 10 80 fps, DirectX 11 99 fps, DirectX 12 49 fps and GPU Compute 6,122 ops/s, across 54,233 submitted results. Frames per second are PassMark test-scene rates, not game frame rates.

As stated by PassMark

Category Desktop

Bus interface PCIe 3.0 x16

Max memory 8 GB

Core clock 1506 MHz

Memory clock 2002 MHz

DirectX 12.0

OpenGL 4.5

Max TDP 150 W

First benchmarked 2016-06-11

Samples 54,233

PassMark listing (collected 2026-09-30)

PassMark's own listing for the NVIDIA GeForce GTX 1070 states the PCIe 3.0 x16 interface, up to 8 GB of memory, a core clock of 1506 MHz, DirectX 12.0 and OpenGL 4.5, first benchmarked on 2016-06-11. These are PassMark's figures, shown separately from the specification tables above.

Not to be confused with

This page covers the NVIDIA GeForce GTX 1070 specifically. It is a different product from NVIDIA GeForce GTX 1070 Mobile, NVIDIA GeForce GTX 1070 Ti, NVIDIA GeForce GTX 1070 with Max-Q Design, NVIDIA GeForce GTX 1070 GDDR5X, NVIDIA GeForce GTX 1070 Max-Q, which have their own specifications. Check the exact model name before comparing figures.

Graphics processor

Architecture Pascal

Codename GP104-200-A1

Chip Not recorded

Process node 16 nm

Transistors 7,200 M

Die size 314 mm²

The NVIDIA GeForce GTX 1070 is based on the Pascal architecture, uses the GP104-200-A1 graphics processor, is manufactured on a 16 nm process, contains 7,200 million transistors and has a die size of 314 mm².

Shader configuration

Shading units 1,920

Compute units Not recorded

Streaming multiprocessors 15

Execution units Not recorded

Texture units (TMUs) 120

Render output units (ROPs) 64

Ray tracing cores Not recorded

Tensor / AI cores Not recorded

XMX engines Not recorded

Infinity cache Not recorded

The NVIDIA GeForce GTX 1070 has 1,920 shading units, 15 streaming multiprocessors, 120 texture mapping units and 64 render output units.

The NVIDIA GeForce GTX 1070 does not use XMX engines; those are specific to Intel Arc graphics. Infinity Cache is an AMD architectural feature and does not apply to the NVIDIA GeForce GTX 1070. Feex has no recorded ray tracing core count for the NVIDIA GeForce GTX 1070.

Clock speeds

Base clock 1.51 GHz

Boost clock 1.68 GHz

Game clock Not recorded

Memory clock 2.00 GHz

Effective memory clock Not recorded

The NVIDIA GeForce GTX 1070 runs at a base clock of 1.51 GHz and boosts to 1.68 GHz.

Memory

Size 8 GB

Type GDDR5

Bus width 256-bit

Bandwidth 256.3 GB/s

The NVIDIA GeForce GTX 1070 is equipped with 8 GB of GDDR5 memory, uses a 256-bit memory bus and delivers 256.3 GB/s of memory bandwidth.

Board and power

The NVIDIA GeForce GTX 1070 has a board power rating of 150 W and it connects over PCIe 3.0 x16.

Board power (TDP) 150 W

Total board power Not recorded

Suggested PSU Not recorded

Power connectors Not recorded

Slot width Not recorded

Length Not recorded

Width Not recorded

Height Not recorded

Cooler Not recorded

Max temperature Not recorded

Bus interface PCIe 3.0 x16

Market

Launched August 16, 2016

Launch price $379

Status Not recorded

Form factor Not recorded

Segment Desktop

Series GeForce GTX 10 Series

The NVIDIA GeForce GTX 1070 was released on August 16, 2016 and launched at a price of $379.

Benchmarks

PassMark G3D 13,513

PassMark G2D 848

Rank #213

Samples 54,233

Graphics and compute APIs

The NVIDIA GeForce GTX 1070 supports DirectX 12, OpenGL 4.6, Vulkan 1.4 and CUDA compute capability 6.1.

DirectX 12

OpenGL 4.6

Vulkan 1.4

CUDA compute capability 6.1

Feex has no recorded OpenCL version for the NVIDIA GeForce GTX 1070.

Features

The NVIDIA GeForce GTX 1070 has 1 supported feature recorded outside the media engine. A feature that no source mentions is shown as not listed, never as unsupported.

Compute and AI

Supported: CUDA Compute capability 6.1

Support for NVIDIA's CUDA computing platform, used by many creative, scientific and AI applications.

Not listed (2)

No source Feex holds states whether the NVIDIA GeForce GTX 1070 supports Tensor cores and NVLink / SLI. That is silence, not a statement that they are unsupported.

The NVIDIA GeForce GTX 1070 supports CUDA (Compute capability 6.1) under Compute and AI.

Media engine

The NVIDIA GeForce GTX 1070 provides hardware encode for H.264 (AVC) and HEVC (H.265) and hardware decode for H.264 (AVC), HEVC (H.265) and VP9. It does not support hardware encode for AV1 and decode for AV1.

NVIDIA NVENC encoder 6th Generation Encoder engines: 2NVIDIA's dedicated video-encoding engine, used by streaming and capture software; newer generations encode more efficiently.

NVIDIA NVDEC decoder 3rd Generation Decoder engines: 1NVIDIA's dedicated video-decoding engine; newer generations support more codecs and formats.

Hardware video codec support of the NVIDIA GeForce GTX 1070
Codec	Encode	Decode
H.264 (AVC)	Supported4:4:4: Yes	Supported
HEVC (H.265)	Supported4:2:2: No; 4:4:4: Yes; 10-bit: Yes; B-frames: No; 8K: Yes	Supported4:4:4: No
AV1	Not supported	Not supported
VP9	Not stated by the vendor	Supported

supported explicitly not supported not stated by the vendor

Media engines recorded for the NVIDIA GeForce GTX 1070: NVIDIA NVENC encoder (6th Generation, encoder engines: 2) and NVIDIA NVDEC decoder (3rd Generation, decoder engines: 1).

Naming and aliases

The NVIDIA GeForce GTX 1070 is also known by other names: PassMark also lists it as NVIDIA GeForce GTX 1070 (Mobile).

Other names (PassMark) NVIDIA GeForce GTX 1070 (Mobile)

Frequently asked questions

How much VRAM does the NVIDIA GeForce GTX 1070 have?

The NVIDIA GeForce GTX 1070 has 8 GB of GDDR5 memory on a 256-bit bus. Its memory bandwidth is 256.3 GB/s.

How much power does the NVIDIA GeForce GTX 1070 use and what power supply does it need?

The NVIDIA GeForce GTX 1070 has a board power rating of 150 W.

How fast is the NVIDIA GeForce GTX 1070?

The NVIDIA GeForce GTX 1070 scores 13,513 in the PassMark G3D benchmark, higher than 92.4% of the 2,658 GPUs benchmarked. Its PassMark rank is #213. In the PassMark DirectX 12 test it averages 49 fps.

Does the NVIDIA GeForce GTX 1070 support AV1 encoding?

No. Feex records AV1 hardware encoding as explicitly not supported on the NVIDIA GeForce GTX 1070.

What is the CUDA compute capability of the NVIDIA GeForce GTX 1070?

The NVIDIA GeForce GTX 1070 has CUDA compute capability 6.1.

What bus interface does the NVIDIA GeForce GTX 1070 use?

The NVIDIA GeForce GTX 1070 connects over PCIe 3.0 x16.

When was the NVIDIA GeForce GTX 1070 released and how much did it cost at launch?

The NVIDIA GeForce GTX 1070 was released on August 16, 2016 and launched at a price of $379.

Corrections to this record

After an audit, 2 values on the NVIDIA GeForce GTX 1070 record were corrected. Each change is listed with its old value, new value, rule and sources.

Transistors: ~~7,000 million~~ → 7,200 million. Rule: Transistor count restored to full precision. stored 7000 is 7200 truncated to whole billions. Sources: Wikipedia: List of Nvidia graphics processing units (revision 1377107724); Wikipedia: List of Nvidia desktop graphics processing units (revision 1375708460).
Compute units: 15 cleared (now Not recorded). Rule: NVIDIA SM count moved out of compute units. compute units 15 on an NVIDIA GPU is its SM count (stated by the Wikipedia list articles). Sources: Wikipedia: List of Nvidia graphics processing units (revision 1377107724); Wikipedia: List of Nvidia desktop graphics processing units (revision 1375708460).

The audit log is public: all changes for this GPU, the corrections overview and the method.

Similar performance

NVIDIA GeForce RTX 2080 Super with Max-Q Design

NVIDIA RTX 1000 Ada Generation Laptop GPU

Compare the NVIDIA GeForce GTX 1070

Side-by-side specification comparisons against cards in the same performance band.

vs AMD Radeon RX 6600S vs NVIDIA RTX A2000