NVIDIA GeForce GTX 1070 Ti
The NVIDIA GeForce GTX 1070 Ti is a graphics card released on November 2, 2017, built on the Pascal architecture using a 16 nm process. It has 2,432 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 180 W board power rating. It scores 14,671 in the PassMark G3D benchmark. It supports DirectX 12, OpenGL 4.6, Vulkan 1.4 and CUDA compute capability 6.1.
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.
Performance
The NVIDIA GeForce GTX 1070 Ti scores 14,671 in the PassMark G3D benchmark, higher than 93.4% of the 2,658 GPUs benchmarked (PassMark rank #184), measured across 13,107 submitted results. Its PassMark G2D score is 876.
PassMark workload tests
In the PassMark workload tests the NVIDIA GeForce GTX 1070 Ti averages DirectX 9 207 fps, DirectX 10 88 fps, DirectX 11 107 fps, DirectX 12 52 fps and GPU Compute 7,169 ops/s, across 13,107 submitted results. Frames per second are PassMark test-scene rates, not game frame rates.
As stated by PassMark
PassMark's own listing for the NVIDIA GeForce GTX 1070 Ti states the PCIe 3.0 x16 interface, up to 8 GB of memory, a core clock of 1607 MHz, DirectX 12 and OpenGL 4.6, first benchmarked on 2017-11-04. 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 Ti specifically. It is a different product from NVIDIA GeForce GTX 1070, NVIDIA GeForce GTX 1070 Mobile, 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
The NVIDIA GeForce GTX 1070 Ti is based on the Pascal architecture, uses the GP104-300-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
The NVIDIA GeForce GTX 1070 Ti has 2,432 shading units, 19 streaming multiprocessors, 152 texture mapping units and 64 render output units.
The NVIDIA GeForce GTX 1070 Ti 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 Ti. Feex has no recorded ray tracing core count for the NVIDIA GeForce GTX 1070 Ti.
Clock speeds
The NVIDIA GeForce GTX 1070 Ti runs at a base clock of 1.61 GHz and boosts to 1.68 GHz.
Memory
The NVIDIA GeForce GTX 1070 Ti 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 Ti has a board power rating of 180 W and it connects over PCIe 3.0 x16.
Market
The NVIDIA GeForce GTX 1070 Ti was released on November 2, 2017 and launched at a price of $399.
Benchmarks
Graphics and compute APIs
The NVIDIA GeForce GTX 1070 Ti supports DirectX 12, OpenGL 4.6, Vulkan 1.4 and CUDA compute capability 6.1.
Feex has no recorded OpenCL version for the NVIDIA GeForce GTX 1070 Ti.
Features
The NVIDIA GeForce GTX 1070 Ti 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 6.1Support 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 Ti supports Tensor cores and NVLink / SLI. That is silence, not a statement that they are unsupported.
The NVIDIA GeForce GTX 1070 Ti supports CUDA (Compute capability 6.1) under Compute and AI.
Media engine
The NVIDIA GeForce GTX 1070 Ti 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.
| 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 Ti: NVIDIA NVENC encoder (6th Generation, encoder engines: 2) and NVIDIA NVDEC decoder (3rd Generation, decoder engines: 1).
Frequently asked questions
How much VRAM does the NVIDIA GeForce GTX 1070 Ti have?
The NVIDIA GeForce GTX 1070 Ti 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 Ti use and what power supply does it need?
The NVIDIA GeForce GTX 1070 Ti has a board power rating of 180 W.
How fast is the NVIDIA GeForce GTX 1070 Ti?
The NVIDIA GeForce GTX 1070 Ti scores 14,671 in the PassMark G3D benchmark, higher than 93.4% of the 2,658 GPUs benchmarked. Its PassMark rank is #184. In the PassMark DirectX 12 test it averages 52 fps.
Does the NVIDIA GeForce GTX 1070 Ti support AV1 encoding?
No. Feex records AV1 hardware encoding as explicitly not supported on the NVIDIA GeForce GTX 1070 Ti.
What is the CUDA compute capability of the NVIDIA GeForce GTX 1070 Ti?
The NVIDIA GeForce GTX 1070 Ti has CUDA compute capability 6.1.
What bus interface does the NVIDIA GeForce GTX 1070 Ti use?
The NVIDIA GeForce GTX 1070 Ti connects over PCIe 3.0 x16.
When was the NVIDIA GeForce GTX 1070 Ti released and how much did it cost at launch?
The NVIDIA GeForce GTX 1070 Ti was released on November 2, 2017 and launched at a price of $399.
Corrections to this record
After an audit, 2 values on the NVIDIA GeForce GTX 1070 Ti 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:
19cleared (now Not recorded). Rule: NVIDIA SM count moved out of compute units. compute units 19 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.