NVIDIA RTX 2000 Max-Q Full Specs

Summary

3,072 Shaders 1.46GHz

8GB GDDR6256GB/s

Peak·FP32·FP16 8.94 TFLOPS

Form Factor Soldered

TDP 50W

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP8-16 FP8-16 Tensor Sparse Tensor FP8-32 FP8-32 Tensor Sparse Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth

RTX 2000 Max-Q286.1 TOPSINT4 Tensor Sparse

x1

Top Score3.35 PFLOPS FP4 Tensor SparseDesktop1xGeForce RTX 5090

x11.72

Theoretical Performance

Clock Speed1455MHz UC·Base·Boost·OC

Peak OPS 286.1 TOPSINT4 Tensor Sparse

Tensor FP8-16 71.52 TFLOPS FP8-16 Tensor Sparse 143 TFLOPS Tensor FP8-32 35.76 TFLOPS FP8-32 Tensor Sparse 71.52 TFLOPS

Tensor FP16-16 35.76 TFLOPS FP16-16 Tensor Sparse 71.52 TFLOPS Tensor FP16-32 17.88 TFLOPS FP16-32 Tensor Sparse 35.76 TFLOPS

BF16 8.94 TFLOPS Tensor BF16 17.88 TFLOPS BF16 Tensor Sparse 35.76 TFLOPS

Tensor TF32 8.94 TFLOPS

FP32 8.94 TFLOPS

FP64 139.7 GFLOPS

Tensor INT4 143 TOPS

Tensor INT8 71.52 TOPS

Ray 20.66 TOPS

Pixel Rate 69.8 GPixel/s

Texture Rate 139.7 GTexel/s

Core Config

Shaders 3,072 Shaders

TMUs 96 TMUs

ROPs 48 ROPs

Tensor Cores 96 T-Cores

RT Cores 24 RT-Cores

SMs 24 SMs

Clocks

Base Clock 930MHz

Boost Clock 1.46GHz

Cache

L1 64KB/SM Tex

L2 Cache 12MB shared

Memory

8GB GDDR6

Memory Bus 128-bit

Memory Speed 16GT/s

Memory Bandwidth 256GB/s

ECC No

Power & Thermals

TDP 50W

Video Output

Max Resolution 7680x4320

Refresh Rate Calculator 7680x4320 Resolution8K UHD Refresh Rate 60Hz

Multi-Monitor 4

Adaptive Sync G-Sync FreeSync

DSC Supported

HDCP HDCP 2.3

API Support

Shader Model 6.6

DirectX DirectX 12 Direct3D 12_3

OpenGL 4.6 OpenCL 3 Vulkan 1.3

CUDA 8.9 PureVideo HD VP12 VDPAU Feature Set L

Encoder

Encoder NVENC 8

Codec AVC (H.264) HEVC (H.265) AV1

Decoder

Decoder NVDEC 5

Codec MPEG-1 MPEG-2 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) AV1

Card

Form Factor Soldered

PCIe PCIe 4.0 x16

Chip

Manufacturer NVIDIA

Chip Designer NVIDIA

Architecture Ada Lovelace

Family RTX Ada

Branding

Codename NV187

Chip Variant AD107

Market Segment Laptop

Release Date Mar 21, 2023

Fabrication

Foundry TSMC

Fabrication Node 4N

Die Size 159mm²

Transistor Count 18.9B

Transistor Density 118.9 MTr/mm²

Images