Feex·GPU
NVIDIA · GeForce RTX 40 Series

NVIDIA GeForce RTX 4070 SUPER

The NVIDIA GeForce RTX 4070 SUPER is a graphics card released on January 17, 2024, built on the Ada Lovelace architecture using a 5 nm process. It has 7,168 shading units, 12 GB of GDDR6X memory on a 192-bit bus, 504.2 GB/s of memory bandwidth, a boost clock of 2.48 GHz and a 220 W board power rating. It scores 29,940 in the PassMark G3D benchmark. It supports DirectX 12 Ultimate, OpenGL 4.6, Vulkan 1.4 and CUDA compute capability 8.9.

Ada LovelaceAD104-350-A15 nm
10/10 key specs recorded · 123 facts

Depth: 63 recorded fields, 29 features, 5 PassMark workloads

Specification data last verified October 1, 2026 against PassMark Videocard Benchmark, NVIDIA GeForce Specifications, 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.

Shading units
7,168cores
56 SMs
Memory
12 GB
GDDR6X · 192-bit
Boost clock
2.48 GHz
1.98 GHz base
Board power
220 W
650 W PSU advised

Performance

The NVIDIA GeForce RTX 4070 SUPER scores 29,940 in the PassMark G3D benchmark, higher than 99.2% of the 2,658 GPUs benchmarked (PassMark rank #22), measured across 15,825 submitted results. Its PassMark G2D score is 1,192.

PassMark G3D Mark
29,940
Rank #22
Faster than 99.2% of 2,658 GPUs
15,825 samples
0relative to the fastest GPU on record (41,928)

PassMark workload tests

DirectX 9 346 fps reference: fastest recorded 526 fps · faster than 98.5% of 1,675 GPUs
DirectX 10 166 fps reference: fastest recorded 231 fps · faster than 97.6% of 1,602 GPUs
DirectX 11 271 fps reference: fastest recorded 362 fps · faster than 97.8% of 1,430 GPUs
DirectX 12 110 fps reference: fastest recorded 213 fps · faster than 97.3% of 1,274 GPUs
GPU Compute 16,926 ops/s reference: fastest recorded 26,591 ops/s · faster than 98.4% 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 RTX 4070 SUPER averages DirectX 9 346 fps, DirectX 10 166 fps, DirectX 11 271 fps, DirectX 12 110 fps and GPU Compute 16,926 ops/s, across 15,825 submitted results. Frames per second are PassMark test-scene rates, not game frame rates.

Theoretical throughput

FP32 (single precision) 36 TFLOPS stated by NVIDIA
AI performance 568 TOPS stated by NVIDIA
Ray tracing 82 TFLOPS stated by NVIDIA

NVIDIA states a peak of FP32 (single precision) 36 TFLOPS, AI performance 568 TOPS and Ray tracing 82 TFLOPS for the NVIDIA GeForce RTX 4070 SUPER.

As stated by PassMark

Category Desktop
Bus interface PCIe 4.0 x16
Max memory 12 GB
Core clock 1980 MHz
Memory clock 1313 MHz
DirectX 12_2
OpenGL 4.6
Max TDP 220 W
First benchmarked 2024-01-17
Samples 15,825

PassMark listing (collected 2026-09-30)

PassMark's own listing for the NVIDIA GeForce RTX 4070 SUPER states the PCIe 4.0 x16 interface, up to 12 GB of memory, a core clock of 1980 MHz, DirectX 12_2 and OpenGL 4.6, first benchmarked on 2024-01-17. These are PassMark's figures, shown separately from the specification tables above.

Not to be confused with

This page covers the NVIDIA GeForce RTX 4070 SUPER specifically. It is a different product from NVIDIA GeForce RTX 4070, NVIDIA GeForce RTX 4070 Laptop GPU, NVIDIA GeForce RTX 4070 Ti, NVIDIA GeForce RTX 4070 Ti SUPER, NVIDIA GeForce RTX 4070 GDDR6, which have their own specifications. Check the exact model name before comparing figures.

Graphics processor

Architecture Ada Lovelace
Codename AD104-350-A1
Chip Not recorded
Process node 5 nm
Transistors 35,800 M
Die size 294 mm²

The NVIDIA GeForce RTX 4070 SUPER is based on the Ada Lovelace architecture, uses the AD104-350-A1 graphics processor, is manufactured on a 5 nm process, contains 35,800 million transistors and has a die size of 294 mm².

Shader configuration

Shading units 7,168
Compute units Not recorded
Streaming multiprocessors 56
Execution units Not recorded
Texture units (TMUs) 224
Render output units (ROPs) 80
Ray tracing cores 56
Tensor / AI cores 224
XMX engines Not recorded
Infinity cache Not recorded

The NVIDIA GeForce RTX 4070 SUPER has 7,168 shading units, 56 streaming multiprocessors, 224 texture mapping units, 80 render output units, 56 ray tracing cores and 224 tensor cores.

The NVIDIA GeForce RTX 4070 SUPER 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 RTX 4070 SUPER.

Clock speeds

Base clock 1.98 GHz
Boost clock 2.48 GHz
Game clock Not recorded
Memory clock 1.31 GHz
Effective memory clock Not recorded

The NVIDIA GeForce RTX 4070 SUPER runs at a base clock of 1.98 GHz and boosts to 2.48 GHz.

Memory

Size 12 GB
Type GDDR6X
Bus width 192-bit
Bandwidth 504.2 GB/s

The NVIDIA GeForce RTX 4070 SUPER is equipped with 12 GB of GDDR6X memory, uses a 192-bit memory bus and delivers 504.2 GB/s of memory bandwidth.

Board and power

The NVIDIA GeForce RTX 4070 SUPER has a board power rating of 220 W, a total board power of 220 W, a power supply of at least 650 W is recommended, power is supplied through 2x PCIe 8-pin cables (adapter in box) OR 300 W or greater PCIe Gen 5 cable. Certain manufacturer models may use 1x PCIe 8-pin cable, the card occupies 2-slot, it is 244 mm long, its width is 112 mm, the maximum operating temperature is 90 °C and it connects over PCIe 4.0.

Board power (TDP) 220 W
Total board power 220 W
Suggested PSU 650 W
Power connectors 2x PCIe 8-pin cables (adapter in box) OR 300 W or greater PCIe Gen 5 cable. Certain manufacturer models may use 1x PCIe 8-pin cable
Slot width 2-slot
Length 244 mm
Width 112 mm
Height Not recorded
Cooler Not recorded
Max temperature 90 °C
Bus interface PCIe 4.0

Market

Launched January 17, 2024
Launch price $599
Status Not recorded
Form factor Not recorded
Segment Desktop
Series GeForce RTX 40 Series

The NVIDIA GeForce RTX 4070 SUPER was released on January 17, 2024 and launched at a price of $599.

Benchmarks

PassMark G3D 29,940
PassMark G2D 1,192
Rank #22
Samples 15,825

Graphics and compute APIs

The NVIDIA GeForce RTX 4070 SUPER supports DirectX 12 Ultimate, OpenGL 4.6, Vulkan 1.4 and CUDA compute capability 8.9.

DirectX 12 Ultimate
OpenGL 4.6
Vulkan 1.4
CUDA compute capability 8.9

Feex has no recorded OpenCL version for the NVIDIA GeForce RTX 4070 SUPER.

Features

The NVIDIA GeForce RTX 4070 SUPER has 19 supported features recorded and 1 feature explicitly listed as not supported outside the media engine. A feature that no source mentions is shown as not listed, never as unsupported.

Rendering

  • Supported: DirectX 12 Ultimate
    Microsoft's top DirectX 12 feature tier, covering hardware ray tracing, mesh shaders, variable-rate shading and sampler feedback.
  • Supported: NVIDIA DLSS DLSS 3
    NVIDIA's AI-based upscaling and frame-generation technology that can raise frame rates in supported games.
  • Supported: Hardware ray tracing 3rd Generation
    Dedicated GPU hardware that speeds up ray-traced lighting, reflections and shadows in supported games and apps.
    Ray tracing units: 56
  • Supported: Vulkan ray tracing
    Support for hardware ray tracing through the Vulkan graphics API.

The NVIDIA GeForce RTX 4070 SUPER supports DirectX 12 Ultimate, NVIDIA DLSS (DLSS 3), Hardware ray tracing (3rd Generation) and Vulkan ray tracing under Rendering.

Compute and AI

  • Supported: CUDA Compute capability 8.9
    Support for NVIDIA's CUDA computing platform, used by many creative, scientific and AI applications.
  • Supported: Tensor cores 4th Generation
    NVIDIA's dedicated matrix-math units used for AI workloads such as DLSS and machine-learning inference.
    Tensor cores: 224
Not supported (1)
  • Explicitly not supported: NVLink / SLI
    What it is: Support for linking two NVIDIA GPUs with a bridge for multi-GPU setups.

The NVIDIA GeForce RTX 4070 SUPER supports CUDA (Compute capability 8.9) and Tensor cores (4th Generation) under Compute and AI. NVLink / SLI is explicitly listed as not supported.

Display features

  • Supported: NVIDIA G-SYNC
    Support for NVIDIA's variable refresh rate technology, which syncs the display to the GPU to reduce tearing and stutter.
  • Supported: HDCP content protection HDCP 2.3
    Support for HDCP, the copy-protection standard that some protected 4K streaming and disc video requires.
  • Supported: VR ready
    The vendor states the GPU meets the requirements for running mainstream PC virtual reality headsets.

The NVIDIA GeForce RTX 4070 SUPER supports NVIDIA G-SYNC, HDCP content protection (HDCP 2.3) and VR ready under Display features.

Platform

  • Supported: Resizable BAR
    Lets the CPU access the GPU's full video memory at once, which can improve performance in some games on supporting systems.
  • Supported: Small-form-factor ready
    The vendor lists the GPU as suitable for compact small-form-factor PC builds.

The NVIDIA GeForce RTX 4070 SUPER supports Resizable BAR and Small-form-factor ready under Platform.

Software and drivers

  • Supported: NVIDIA Freestyle
    NVIDIA game filter feature that adjusts colors and sharpness in supported games.
  • Supported: NVIDIA Game Ready drivers
    Driver branch tuned and released alongside new games.
  • Supported: NVIDIA Broadcast
    NVIDIA software that applies AI noise removal and camera effects for calls and streams.
  • Supported: NVIDIA Omniverse
    Support for NVIDIA's Omniverse platform for collaborative 3D design and simulation.
  • Supported: NVIDIA Reflex
    NVIDIA's latency-reduction technology that lowers the delay between input and what you see in supported games.
  • Supported: RTX Remix
    NVIDIA tooling for modding older games with ray tracing and updated assets.
  • Supported: NVIDIA ShadowPlay
    NVIDIA's built-in tool for recording and streaming gameplay.
  • Supported: NVIDIA Studio drivers
    Driver branch tuned and tested for creative applications.
Not listed (1)

No source Feex holds states whether the NVIDIA GeForce RTX 4070 SUPER supports RTX HDR. That is silence, not a statement that they are unsupported.

The NVIDIA GeForce RTX 4070 SUPER supports NVIDIA Freestyle, NVIDIA Game Ready drivers, NVIDIA Broadcast, NVIDIA Omniverse, NVIDIA Reflex, RTX Remix, NVIDIA ShadowPlay and NVIDIA Studio drivers under Software and drivers.

Media engine

The NVIDIA GeForce RTX 4070 SUPER provides hardware encode for H.264 (AVC), HEVC (H.265) and AV1 and hardware decode for H.264 (AVC), HEVC (H.265), AV1 and VP9.

NVIDIA NVENC encoder 8th Generation Encoder engines: 1NVIDIA's dedicated video-encoding engine, used by streaming and capture software; newer generations encode more efficiently.
NVIDIA NVDEC decoder 5th Generation Decoder engines: 1NVIDIA's dedicated video-decoding engine; newer generations support more codecs and formats.
Hardware video codec support of the NVIDIA GeForce RTX 4070 SUPER
CodecEncodeDecode
H.264 (AVC) Supported4:4:4: YesSupported
HEVC (H.265) Supported4:2:2: No; 4:4:4: Yes; 10-bit: Yes; B-frames: Yes; 8K: YesSupported4:4:4: Yes
AV1 SupportedSupported
VP9 Not stated by the vendorSupported

supported   explicitly not supported   not stated by the vendor

Media engines recorded for the NVIDIA GeForce RTX 4070 SUPER: NVIDIA NVENC encoder (8th Generation, encoder engines: 1) and NVIDIA NVDEC decoder (5th Generation, decoder engines: 1).

Display outputs

The NVIDIA GeForce RTX 4070 SUPER offers outputs HDMI, 3x DisplayPort, up to 4 simultaneous displays, a maximum resolution of 4K at 240Hz or 8K at 60Hz with DSC, HDR and HDCP 2.3. It is stated to be VR ready.

Outputs HDMI, 3x DisplayPort
Max simultaneous displays 4
Max resolution 4K at 240Hz or 8K at 60Hz with DSC, HDR
HDCP 2.3
VR ready Yes

Frequently asked questions

How much VRAM does the NVIDIA GeForce RTX 4070 SUPER have?

The NVIDIA GeForce RTX 4070 SUPER has 12 GB of GDDR6X memory on a 192-bit bus. Its memory bandwidth is 504.2 GB/s.

How much power does the NVIDIA GeForce RTX 4070 SUPER use and what power supply does it need?

The NVIDIA GeForce RTX 4070 SUPER has a board power rating of 220 W. Feex records a suggested power supply of at least 650 W. Power connectors: 2x PCIe 8-pin cables (adapter in box) OR 300 W or greater PCIe Gen 5 cable. Certain manufacturer models may use 1x PCIe 8-pin cable.

How fast is the NVIDIA GeForce RTX 4070 SUPER?

The NVIDIA GeForce RTX 4070 SUPER scores 29,940 in the PassMark G3D benchmark, higher than 99.2% of the 2,658 GPUs benchmarked. Its PassMark rank is #22. In the PassMark DirectX 12 test it averages 110 fps.

Does the NVIDIA GeForce RTX 4070 SUPER support ray tracing?

Yes. The NVIDIA GeForce RTX 4070 SUPER has hardware ray tracing (3rd Generation) with 56 ray tracing cores.

Does the NVIDIA GeForce RTX 4070 SUPER support AV1 encoding?

Yes. The NVIDIA GeForce RTX 4070 SUPER supports AV1 hardware encoding and AV1 hardware decoding.

Does the NVIDIA GeForce RTX 4070 SUPER support DirectX 12 Ultimate?

Yes. The NVIDIA GeForce RTX 4070 SUPER supports DirectX 12 Ultimate.

What is the CUDA compute capability of the NVIDIA GeForce RTX 4070 SUPER?

The NVIDIA GeForce RTX 4070 SUPER has CUDA compute capability 8.9.

What bus interface does the NVIDIA GeForce RTX 4070 SUPER use?

The NVIDIA GeForce RTX 4070 SUPER connects over PCIe 4.0.

When was the NVIDIA GeForce RTX 4070 SUPER released and how much did it cost at launch?

The NVIDIA GeForce RTX 4070 SUPER was released on January 17, 2024 and launched at a price of $599.

Corrections to this record

After an audit, 3 values on the NVIDIA GeForce RTX 4070 SUPER record were corrected. Each change is listed with its old value, new value, rule and sources.

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

Similar performance