P106-090

Key Metrics

Save this GPU, then open another GPU page to compare them side by side.

Identity
Entry Type	Reference GPU
Official Name	NVIDIA P106-090
GPU Codename	GP106
Architecture	Pascal
Launch Date	2017-07-31
Market Segment Notes	Desktop in Mining GPUs
Core Specs
GPU Die	GP106
Chip Variant / Package	BGA-2173
Process Node	TSMC 16 nm
Transistor Count	4.4 billion
Die Size	200 mm²
CUDA Cores	768
SM Count	6
TMUs	48
ROPs	48
Base Clock	1,354 MHz
Boost Clock	1,531 MHz
Pixel Fillrate	73.49 GP/s
Texture Fillrate	73.49 GT/s
FP32 Throughput	2.35 TFLOPS
FP16 Throughput	0.04 TFLOPS
FP64 Throughput	0.07 TFLOPS
Memory
Memory Size	3 GB
Memory Type	GDDR5
Memory Bus Width	192-bit
Memory Clock	2,002 MHz
Memory Bandwidth	192.2 GB/s
L2 Cache	2 MB
L1 Cache	48 KB
Board and Display
TDP / TBP	75 W
Recommended PSU	250 W
Power Connectors	1x 6-pin
Interface	PCIe 1.0 x1
Slot Width	Dual-slot, 250 mm length
Card Length	250 mm
Board Partner Model	Reference or OEM specification
Reference Design	NVIDIA reference design
Software
CUDA Compute Capability	6.1
Shader Model	6.8
DirectX Support	DirectX 12.1
Vulkan Support	Vulkan 1.4
OpenGL Support	OpenGL 4.6
OpenCL Support	OpenCL 3.0

Sources

TechPowerUp GPU SpecsModel-level specification reference for this GPU entryOpen source

RightNow GPU DatabaseOpen GPU database used to cross-check specifications A reference database: good for cross-checking specifications, but not proof of the original release details on its own.Open source