NVIDIA GeForce GTX 1060 vs NVIDIA GeForce GTX 1650

Every spec side by side, from each maker's published figures.

Only show differences

Better figure, where one is clearly better

Share comparison

GeForce GTX 1060 compared with GeForce GTX 1650

	NVIDIAGeForce GTX 1060	NVIDIAGeForce GTX 1650
Overview
Released
Released	July 2016	April 2019
Performance
Chip maker
Chip maker	NVIDIA	NVIDIA
Architecture
Architecture	Pascal	Turing
Shader cores
Shader cores	1,280 or 1,152	896
Boost clock
Boost clock	1,708 MHz or –	1,665 MHz or 1,590 MHz
Architecture
Architecture	Main figures and photo describe the original 6 GB Founders Edition. The 3 GB card has 1152 CUDA cores rather than 1280. Later 9 Gbps GDDR5 and GDDR5X cards were partner designs; unpublished general revision figures remain blank in their configurations.	NVIDIA GPU specification baseline; the photo shows PNY's original stock-clock GDDR5 Single Fan board. The first-sale date is for the original GDDR5 model; a maker first-sale date for GDDR6 was not established.
Manufacturing process
Manufacturing process	16 nm FinFET (original GP106)	–
Ray tracing
Ray tracing	No dedicated RT Cores	No hardware RT Cores
AI cores
AI cores	No Tensor Cores	No Tensor Cores
Upscaling and frame generation
Upscaling and frame generation	No NVIDIA DLSS	No NVIDIA DLSS support
Base clock
Base clock	1506 MHz base and 1708 MHz boost for the original 6 GB and stock-clock 3 GB cards. MSI GAMING X+ 6G (9 Gbps GDDR5) has 1708 MHz boost in Silent Mode, 1784 MHz Gaming Mode and 1809 MHz OC Mode. MSI ARMOR 6GD5X OC specifies 1544 MHz base and 1759 MHz boost; these factory OC figures are not assigned to every GDDR5X card.	Original GDDR5 is 1,485 MHz; GDDR6 is 1,410 MHz
Cache
Cache	1536 KB L2 cache (original GP106)	–
Memory
Video memory
Video memory	6 GB GDDR5, 3 GB GDDR5 or 6 GB GDDR5X	4 GB GDDR5 or 4 GB GDDR6
Memory bus
Memory bus	192-bit (better)	128-bit
Memory bandwidth
Memory bandwidth	192 GB/s or –	128 GB/s or –
Memory detail
Memory detail	Original 6 GB and 3 GB cards have 8 Gbps GDDR5, 192-bit bus and 192 GB/s bandwidth. NVIDIA confirms the later 9 Gbps GDDR5 refresh; MSI GAMING X+ lists 9026 MHz Gaming/Silent and 9126 MHz OC memory speed. MSI ARMOR 6GD5X OC verifies 6 GB GDDR5X, 192-bit bus and 8008 MHz memory speed, but publishes no bandwidth figure. Later revisions' first-sale dates are unverified.	PNY publishes 8 Gbps and 128 GB/sec for GDDR5; its GDDR6 PDF gives 12 Gbps but labels its bandwidth figure as Gbps, so numeric GDDR6 bandwidth is omitted.
Connections and power
Board power
Board power	120 W or –	75 W
Interface
Interface	PCIe 3.0	PCIe 3.0
Display outputs
Display outputs	Original Founders Edition has 3 × DisplayPort 1.3/1.4, HDMI 2.0b and dual-link DVI; partner outputs vary	PNY's pictured GDDR5 Single Fan specification lists DisplayPort 1.4 and DVI-D. Its GDDR6 Dual Fan PDF conflicts internally, listing HDMI 2.0b in the features and HDMI 2.1 in the table; check the selected board.
Maximum resolution
Maximum resolution	7680 × 4320 (PNY stock 3 GB specification)	7680 × 4320 on PNY's specifications
Power connector
Power connector	1 × PCIe 6-pin on the original Founders Edition and stock PNY 3 GB; MSI GAMING X+ uses 1 × 8-pin, and MSI ARMOR GDDR5X OC uses 1 × 8-pin plus 1 × 6-pin	NVIDIA's current comparison table lists one 6-pin for both revisions; PNY's pictured stock GDDR5 card explicitly needs no auxiliary connector, while its GDDR6 Dual Fan needs one 6-pin.
Recommended power supply
Recommended power supply	400 W (PNY stock 3 GB, MSI GAMING X+ and MSI ARMOR GDDR5X OC)	NVIDIA specifies 300 W; requirements depend on the system and partner card
Slot width
Slot width	2-slot original Founders Edition; partner cards vary	PNY's pictured GDDR5 Single Fan and GDDR6 Dual Fan are dual-slot designs
Size (reference card)
Size (reference card)	–	No retail Founders Edition; pictured PNY GDDR5 Single Fan is 1.61 × 6.22 × 4.92 inches. PNY GDDR6 Dual Fan is 188.3 × 115.1 × 39.3 mm.
Video encode and decode
Video encode and decode	–	NVIDIA identifies the original encoder as Volta; GDDR6 cards can have Volta or Turing encoders depending on whether the GPU is TU117 or TU106/TU116. PNY specifies PCIe 3.0 x16 for both pictured/reference partner designs.