NVIDIA GA10B 28SM Full Specs

Summary

1,792 Shaders 930MHz

Shared Memory204.8GB/sLPDDR5

Peak·FP32·FP16 3.33 TFLOPS

Form Factor iGPU

TDP Shared

Highlights

Peak OPS

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

GA10B 28SM213.3 TOPSINT4 Tensor Sparse

x1

Top Score3.35 PFLOPS FP4 Tensor SparseDesktop1xGeForce RTX 5090

x15.71

Theoretical Performance

Clock Speed930MHz UC·Boost·OC

Peak OPS 213.3 TOPSINT4 Tensor Sparse

Tensor FP16-16 26.66 TFLOPS FP16-16 Tensor Sparse 53.33 TFLOPS Tensor FP16-32 26.66 TFLOPS FP16-32 Tensor Sparse 53.33 TFLOPS

Tensor BF16 26.66 TFLOPS BF16 Tensor Sparse 53.33 TFLOPS

Tensor TF32 13.33 TFLOPS

FP32 3.33 TFLOPS

Tensor INT4 106.7 TOPS

Tensor INT8 53.33 TOPS

Pixel Rate 22.3 GPixel/s

Texture Rate 13 GTexel/s

Core Config

Shaders 1,792 Shaders

TMUs 14 TMUs

ROPs 24 ROPs

Tensor Cores 56 T-Cores

SMs 14 SMs

Clocks

Boost Clock 930MHz

Cache

L1 64KB/SM Tex

L2 Cache 4MB shared

Memory

Shared MemoryLPDDR5

Memory Bus 256-bit

Memory Speed 6.4GT/s

Memory Bandwidth 204.8GB/s

ECC No

Video Output

Adaptive Sync G-Sync FreeSync

DSC Not Supported

API Support

Shader Model 6.7

DirectX DirectX 12 Direct3D 12_2

OpenGL 4.6 OpenCL 3 Vulkan 1.3

CUDA 8.7 PureVideo HD VP11 VDPAU Feature Set K

Encoder

Encoder NVENC 7

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

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 iGPU

Chip

Manufacturer NVIDIA

Chip Designer NVIDIA

Architecture Ampere

Family Jetson

Branding

Codename Hercules

Market Segment Embedded

Release Date Oct 1, 2022

Fabrication

Foundry Samsung

Fabrication Node 8N

Transistor Count 17B

Images

Used In

CPUs NVIDIAAGX Orin 32GB8 Cores

Competitors

NVIDIAGA10B 28SM vs GPU NVIDIAGA10B 32SM NVIDIAGA10B 28SM vs GPU NVIDIAGA10B 16SM 765MHz NVIDIAGA10B 28SM vs GPU NVIDIAGA10B 16SM 625MHz Show 12 more