GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

GeForce RTX 4070 Max-Q

Graphics processor

Video memory: 8 GB^*
Memory bus: 128 bit^*
Rated memory bandwidth: 256 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: Ada Lovelace^*
Process node: 5 nm^*
GPU cores: 4,608^*
GPU base clock: 735 MHz^*
Graphics interface: PCIe 4.0 x8^*
Reported chip die area: 188 mm²^*
Transistors: 22,900 million^*
GPU boost clock: 1,230 MHz^*
GPU L2 cache: 32 MB^*
Graphics processor: AD106^*
Texture mapping units: 144^*
Raster output units: 48^*
Streaming multiprocessors: 36^*
Tensor cores: 144^*
Ray tracing cores: 36^*
Chip foundry: TSMC^*
Card or module format: IGP^*
Declared GPU TDP: 35 W^*
External power connectors: None^*
DirectX / feature level: 12 Ultimate (12_2)^*
OpenGL: 4.6^*
OpenCL: 3.0^*
Vulkan: 1.4^*
CUDA compute capability: 8.9^*
Shader model: 6.9^*

Memory & storage

Memory options: 8^*
Video memory: 8 GB^*
Video memory type: GDDR6^*
Memory bus: 128 bit^*
Rated memory bandwidth: 256 GB/s^*

Power specifications

Thermal design power: 35 W^*

System configuration

Detailed specifications

Specifications 1 · 7 fields

Product Name: GeForce RTX 4070 Max-Q^*
GPU Chip: AD106^*
Bus: PCIe 4.0 x16^*
Memory: 8 GB, GDDR6, 128 bit^*
GPU clock: 735^* MHz
Memory clock: 1,750^* MHz
Shaders TMUs ROPs: 4608 / 144 / 48^*

Specifications 2 · 29 fields

proc transistors: 22,900 million^*
proc die size: 188^* mm²
cores: 4,608^*
tensor cores: 144^*
rt cores: 36^*
sm count: 36^*
base clock: 735^*
boost clock: 1,230^*
memory clock: 2,000^*
ram: 8^*
name: NVIDIA GeForce RTX 4070 Max-Q^*
ram type: GDDR6^*
bus width: 128^*
bus interface: PCIe 4.0 x8^*
ram bandwidth: 256^* GB/s
fp16 performance: 11.34^*
fp32 performance: 11.34^*
fp64 performance: 0.1771^*
tdp: 35^* W
slot width: IGP^*
api cuda: 8.9^*
is retail board: No^*
gpi value: 6.21^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Ada Lovelace^*
card release date: 2023-01-03^*
proc foundry: TSMC^*
proc process size: 5^* nm

Specifications 3 · 39 fields

CUDA compute capability

8.9^*

DirectX / feature level

12 Ultimate (12_2)^*

OpenCL

3.0^*

OpenGL

4.6^*

Shader model

6.9^*

Vulkan

1.4^*

Architecture

Ada Lovelace^*

Graphics interface

PCIe 4.0 x8^*

Memory bus

128^* bit

Reported shader processors

4,608^*

Reported theoretical FP16 peak

11.34^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

11.34^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

0.1771^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

128 KB (per SM)^*

Declared GPU L2 cache

32 MB^*

Reported display outputs

Portable Device Dependent^*

Theoretical pixel fill rate

59.04 GPixel/s^*

External power connectors

None^*

Reported chip die area

188 mm²^*

Chip foundry

TSMC^*

Process node declaration

5 nm^*

Transistors

22,900 million^*

Graphics processor

AD106^*

Reported video memory

8^* GB

Rated memory bandwidth

256.0 GB/s^*

Video memory type

GDDR6^*

Raster output units

48^*

Ray tracing cores

36^*

Reported shading units

4,608^*

Card or module format

IGP^*

Streaming multiprocessors

36^*

2:4 tensor sparsity

Yes^*

Declared GPU TDP

35 W^*

Tensor cores

144^*

Theoretical texture fill rate

177.1 GTexel/s^*

Texture mapping units

144^*

GPU cores

4,608^*

Video memory

8^* GB

Video memory type

GDDR6^*

Specifications 4 · 8 fields

Product Name: GeForce RTX 4070 Max-Q^*
GPU Chip: AD106^*
Released: Jan 3rd, 2023^*
Bus: PCIe 4.0 x16^*
Memory: 8 GB, GDDR6, 128 bit^*
GPU clock: 735^* MHz
Memory clock: 2,000^* MHz
Shaders / TMUs / ROPs: 4608 / 144 / 48^*

Specifications 5 · 54 fields

Brand: NVIDIA^*
Top BUS WIDTH: 128^* bit
Graphics Processor GPU Name: AD106^*
Graphics Processor Architecture: Ada Lovelace^*
Render Config SM Count: 36^*
Graphics Features CUDA: 8.9^*
Render Config Tensor Cores: 144^*
Graphics Processor Process Size: 5^* nm
Graphics Processor Transistors: 22,900 million^*
Graphics Processor Die Size: 188^* mm²
Name: GeForce RTX 4070 Max-Q^*
Clock Speeds Memory Clock: 2000 MHz 16 Gbps effective^*
Memory Memory Size: 8^* GB
Memory Memory Type: GDDR6^*
Memory Memory Bus: 128^* bit
Memory Bandwidth: 256^* GB/s
Render Config TMUs: 144^*
Top GRAPHICS PROCESSOR: AD106^*
Render Config ROPs: 48^*
Theoretical Performance Pixel Rate: 59.04 GPixel/s
Theoretical Performance Texture Rate: 177.1 GTexel/s
Board Design Slot Width: IGP^*
Board Design TDP: 35^* W
Board Design Outputs: Portable Device Dependent^*
Graphics Features DirectX: 12 Ultimate (12_2)^*
Graphics Features OpenGL: 4.6^*
Graphics Features OpenCL: 3^*
Graphics Features Vulkan: 1.3^*
source file: nvidia2023.json^*
Graphics Processor Foundry: TSMC^*
Recommended Resolutions: Good:1600x900 | Playable:1920x1080 | Unplayable:2560x1440^*
Graphics Processor GPU Variant: GN21-X6^*
Graphics Processor Density: 121.8M / mm²^*
Mobile Graphics Release Date: Jan 3rd, 2023^*
Top TMUS: 144^*
Mobile Graphics Generation: GeForce 40 Mobile^*
Mobile Graphics Production: Active^*
Mobile Graphics Bus Interface: PCIe 4.0 x8^*
Top ROPS: 48^*
Mobile Graphics Successor: GeForce 50 Mobile^*
Mobile Graphics Predecessor: GeForce 30 Mobile^*
Clock Speeds Base Clock: 735^* MHz
Clock Speeds Boost Clock: 1,230^* MHz
Graphics Features Shader Model: 6.8^*
Top CORES: 4,608^*
Render Config Shading Units: 4,608^*
Render Config L2 Cache: 32^* MB
Top MEMORY SIZE: 8^* GB
Theoretical Performance FP32 (float): 11.34^* TFLOPS
Theoretical Performance FP64 (double): 177.1 GFLOPS (1:64)
Render Config L1 Cache: 128 KB (per SM)^*
Theoretical Performance FP16 (half): 11.34 TFLOPS (1:1)
Top MEMORY TYPE: GDDR6^*
Render Config RT Cores: 36^*

Specifications 6 · 14 fields

manufacturer: NVIDIA^*
rop: 64^*
igp: No^*
bus: PCIe 4.0 x16^*
memType: GDDR6^*
gpuChip: GA104^*
productName: GeForce RTX 4070 Max-Q^*
releaseYear: 2,023^*
memSize: 8^*
memBusWidth: 128^*
gpuClock: 855^*
memClock: 1,750^*
unifiedShader: 4,096^*
tmu: 128^*

* Provisional data