GeForce GTX 950A

Maxwell GeForce 900A Desktop DDR3 2015 NVIDIA

Key Metrics

Launch Date: 2015-03-13
CUDA Cores: 640
Memory: 2 GB DDR3
Memory Bandwidth: 32.03 GB/s
TDP/TBP: 75 W
Interface: MXM-B (3.0)

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

GPU Specs

Identity
Entry Type	Reference GPU
Official Name	NVIDIA GeForce GTX 950A
GPU Codename	GM107
Architecture	Maxwell
Launch Date	2015-03-13
Market Segment Notes	Desktop in GeForce 900A
Core Specs
GPU Die	GM107
Chip Variant / Package	FCBGA-908
Process Node	TSMC 28 nm
Transistor Count	1.87 billion
Die Size	148 mm²
CUDA Cores	640
SM Count	5
TMUs	40
ROPs	16
Base Clock	993 MHz
Boost Clock	1,124 MHz
Pixel Fillrate	17.98 GP/s
Texture Fillrate	44.96 GT/s
FP32 Throughput	1.44 TFLOPS
FP64 Throughput	0.04 TFLOPS
Memory
Memory Size	2 GB
Memory Type	DDR3
Memory Bus Width	128-bit
Memory Clock	1,001 MHz
Memory Bandwidth	32.03 GB/s
L2 Cache	2 MB
L1 Cache	64 KB
Board and Display
TDP / TBP	75 W
Power Connectors	None
Interface	MXM-B (3.0)
Slot Width	MXM Module
Board Partner Model	Reference or OEM specification
Reference Design	NVIDIA reference design
Software
CUDA Compute Capability	5.0
Shader Model	5.1
DirectX Support	DirectX 11.0
Vulkan Support	Vulkan 1.4
OpenGL Support	OpenGL 4.6
OpenCL Support	OpenCL 3.0

Why It Mattered

GeForce GTX 950A belongs to the Maxwell and GeForce 900A era around 2015, when PC graphics cards varied heavily by bus, memory chips, BIOS, cooler, and display outputs. Tracking the exact model helps retro builders distinguish period-correct boards from similarly named variants.

Sources

Independent reference sources

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

Reference databases

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

Why It Mattered

GeForce 920A

GeForce 930A

GeForce 940A

GeForce 945A

Independent reference sources

Reference databases