GPU Wiki

Compare GPUs

Select up to four GPU Wiki entries to compare matching specifications row by row. The comparison uses the site database and keeps generation-specific specs visibly separate.

Popular comparisons

Add a third or fourth GPU
Spec GB10
Overview
Product name NVIDIA GB10
Architecture Blackwell 2.0
Generation / family NVIDIA B-Series
GPU codename GB20B
Launch date 2025-10-15
Market segment Desktop in NVIDIA B-Series
Board type / entry type Reference GPU
GPU
Process node TSMC 5 nm
GPU chip GB20B
SM / multiprocessor count 48
CUDA Cores 6144
Tensor Cores 384
RT Cores 48
ROPs 48
TMUs 384
Clocks
Base / Core clock 1,665 MHz
Boost clock 2,418 MHz
Memory clock 1,067 MHz
Memory
Memory size 128 GB
Memory type LPDDR5X
Memory bus width 256-bit
Memory bandwidth 273.2 GB/s
Bus / Interface
Bus interface PCIe 5.0 x16
AGP / PCI / PCIe distinction PCIe
Power
TDP / TBP / board power 140 W
Recommended PSU 300 W
Power connectors None
Slot width IGP, 150 mm length, 150 mm width
Display / Media
Display outputs 1x HDMI
Features
CUDA support 12.1
Ray tracing support Hardware RT units present
Performance / Benchmarks
FP32 throughput 29.71 TFLOPS
FP16 throughput 29.71 TFLOPS
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.

Frame rates compare runs of the same game at the same quality preset on one test system. DLAA counts as native resolution, because it applies anti-aliasing at full render resolution rather than upscaling; DLSS and FSR upscaling are never counted as native. Where a capture named ray tracing without a readable on or off value, it is read as on.