CMP 170HX 8 GB

Key Metrics

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

Identity
Entry Type	Reference GPU
Official Name	NVIDIA CMP 170HX 8 GB
GPU Codename	GA100
Architecture	Ampere
Launch Date	2021-09-01
Market Segment Notes	Desktop in Mining GPUs
Core Specs
GPU Die	GA100
Chip Variant / Package	BGA-2743
Process Node	TSMC 7 nm
Transistor Count	54.2 billion
Die Size	826 mm²
CUDA Cores	4480
SM Count	70
TMUs	280
ROPs	128
AI Units / Tensor Cores	280
Base Clock	1,140 MHz
Boost Clock	1,410 MHz
Pixel Fillrate	180.5 GP/s
Texture Fillrate	394.8 GT/s
FP32 Throughput	12.63 TFLOPS
FP16 Throughput	50.53 TFLOPS
FP64 Throughput	6.32 TFLOPS
Memory
Memory Size	8 GB
Memory Type	HBM2e
Memory Bus Width	4,096-bit
Memory Clock	1,458 MHz
Memory Bandwidth	1,490 GB/s
L2 Cache	8 MB
L1 Cache	192 KB
Board and Display
TDP / TBP	250 W
Recommended PSU	600 W
Power Connectors	2x 8-pin
Interface	PCIe 1.0 x4
Slot Width	IGP
Board Partner Model	Reference or OEM specification
Reference Design	NVIDIA reference design
Software
CUDA Compute Capability	8.0
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