NVIDIA GeForce GT 745M vs NVIDIA GeForce GTX 1050 Ti Comparison

NVIDIA
GEFORCE

NVIDIA GeForce GT 745M

CORE STATE GK107
VRAM 2 GB
CLOCK SPEED —
TDP 45 W
BUS WIDTH 128 bit
ARCHITECTURE Kepler
nm
PROCESS 28 nm
LAUNCH DATE 2013
VS
NVIDIA
GEFORCE

GeForce GTX 1050 Ti

CORE STATE GP107
VRAM 4 GB
CLOCK SPEED 1392 MHz
TDP 75 W
BUS WIDTH 128 bit
ARCHITECTURE Pascal
nm
PROCESS 14 nm
LAUNCH DATE 2016

PERFORMANCE BENCHMARKS

geekbench_metal
2,777
7,834
geekbench_opencl
3,580
18,129
geekbench_vulkan
5,502
10,001
3dmark_3dmark_steel_nomad_dx12
N/A
305
passmark_directx_10
N/A
31
passmark_directx_11
N/A
45
passmark_directx_12
N/A
26
passmark_directx_9
N/A
104
passmark_g2d
N/A
651
passmark_g3d
N/A
6,340
passmark_gpu_compute
N/A
2,652

Analysis: NVIDIA GeForce GT 745M vs NVIDIA GeForce GTX 1050 Ti

The data is unambiguous: the NVIDIA GeForce GTX 1050 Ti is in a completely different performance class than the NVIDIA GeForce GT 745M. Across every shared benchmark, the GTX 1050 Ti delivers overwhelming victories, with margins ranging from 81.8% to 406.4%. The GT 745M, a Kepler-era mobile chip, is decisively outclassed by the Pascal-based GTX 1050 Ti in every measurable way. For any user choosing between these two, the GTX 1050 Ti is the only rational choice for gaming or GPU-accelerated workloads, assuming system compatibility allows for its dual-slot, 75 W discrete design.

The Verdict

From the benchmark data, the GTX 1050 Ti is the clear winner, taking all three head-to-head tests. The GT 745M’s best showing is in the Vulkan test, where it scores 5502 against the GTX 1050 Ti’s 10001, a deficit of 81.8%. In OpenCL, the gap is catastrophic: the GTX 1050 Ti scores 18129 versus 3580 for the GT 745M, a 406.4% advantage. The GTX 1050 Ti also holds a 182.1% lead in Geekbench Metal, scoring 7834 to the GT 745M’s 2777. The verdict is simple: the GTX 1050 Ti is for anyone needing actual graphics performance, while the GT 745M is only relevant in legacy laptops where it is already installed, and even then, it should be considered a basic display adapter rather than a gaming solution.

The data also places the two GPUs in similar overall percentile ranks, with the GTX 1050 Ti at the 25th percentile of all GPUs and the GT 745M at the 23rd. However, this similarity in percentile is misleading. The GTX 1050 Ti’s average benchmark score of 4193 is only 6% higher than the GT 745M’s 3953, but this average is dragged down by the inclusion of low-level DirectX tests (e.g., Passmark DirectX 9 score of 104) that are not present in the GT 745M’s data set. In the tests where both GPUs are measured, the GTX 1050 Ti is vastly superior. For a new purchase, the GTX 1050 Ti is the only option with any merit.

Architecture Differences

The architectural divide between these two GPUs is generational and fundamental. The GTX 1050 Ti is built on the Pascal architecture using the GP107 chip, fabricated on a 14 nm process at Samsung. In contrast, the GT 745M uses the older Kepler architecture with the GK107 chip, built on a 28 nm process at TSMC. This process shrink allows the GTX 1050 Ti to pack 3,300 million transistors into a 132 mm² die, yielding a transistor density of 25.0M per mm². The GT 745M, with 1,270 million transistors on a 118 mm² die, has a density of just 10.8M per mm². The GTX 1050 Ti is a dramatically more complex and efficient chip.

The compute resources are also heavily skewed. The GTX 1050 Ti features 768 shading units, 48 texture mapping units (TMUs), and 32 render output units (ROPs). The GT 745M has only 384 shading units, 32 TMUs, and 16 ROPs. This translates to a peak FP32 throughput of 2.138 TFLOPS for the GTX 1050 Ti versus a mere 421.6 GFLOPS for the GT 745M. The GTX 1050 Ti also supports FP16 at 33.41 GFLOPS, a feature the GT 745M lacks entirely. Memory configurations differ too: the GTX 1050 Ti has 4 GB of GDDR5 on a 128-bit bus, while the GT 745M has 2 GB of GDDR5 on the same 128-bit bus. The GTX 1050 Ti’s memory clock of 1752 MHz (7 Gbps effective) yields 112.1 GB/s of bandwidth, nearly double the GT 745M’s 64.00 GB/s from its 1000 MHz (4 Gbps effective) memory clock.

Where Each One Wins

Based on the head-to-head benchmarks, the GTX 1050 Ti wins in every category where both are tested. In Geekbench Metal, a measure of GPU compute performance on Apple’s API, the GTX 1050 Ti is 182.1% faster. In Geekbench OpenCL, a cross-platform compute standard, the GTX 1050 Ti’s 18129 score absolutely dwarfs the GT 745M’s 3580. For Vulkan, a modern graphics and compute API, the GTX 1050 Ti again dominates with a 81.8% lead. There is no workload in the data where the GT 745M comes out ahead.

The GT 745M’s only “wins” are in the field of power and physical footprint. It has a 45 W TDP versus the GTX 1050 Ti’s 75 W, and it is an IGP (integrated graphics processor) with its size being “Portable Device Dependent,” meaning it is soldered onto a laptop motherboard. The GTX 1050 Ti, by contrast, is a dual-slot discrete card with no power connectors, requiring a 250 W power supply. For a user with a legacy laptop that only supports the GT 745M, there is no choice. For anyone building or upgrading a desktop, the GTX 1050 Ti is the only viable option.

FAQ

Q: Which GPU is faster in Geekbench OpenCL?

A: The NVIDIA GeForce GTX 1050 Ti is overwhelmingly faster, scoring 18129 compared to the GT 745M’s 3580, a 406.4% difference.

Q: What is the performance gap in the Vulkan benchmark?

A: The GTX 1050 Ti scores 10001, while the GT 745M scores 5502. The GTX 1050 Ti leads by 81.8%.

Q: Does the GT 745M have any advantage in memory bandwidth?

A: No. The GTX 1050 Ti has 112.1 GB/s of bandwidth, while the GT 745M has only 64.00 GB/s, despite both using a 128-bit bus.

Q: Are both GPUs from the same architectural generation?

A: No. The GTX 1050 Ti uses the Pascal architecture (GP107 chip), while the GT 745M uses the older Kepler architecture (GK107 chip).

Q: Which GPU has more shading units?

A: The GTX 1050 Ti has 768 shading units, exactly double the GT 745M’s 384 shading units.

Q: What is the average benchmark score for each GPU?

A: The GTX 1050 Ti has an average benchmark score of 4193, while the GT 745M has an average of 3953.

Head-to-Head Benchmarks

The three shared benchmarks paint a picture of total domination for the GTX 1050 Ti. The largest margin is in Geekbench OpenCL, where the GTX 1050 Ti scores 18129 versus 3580 for the GT 745M. This 406.4% delta reflects the massive difference in raw compute throughput, driven by the GTX 1050 Ti’s 2.138 TFLOPS FP32 performance against the GT 745M’s 421.6 GFLOPS. In practical terms, this means the GTX 1050 Ti will complete OpenCL compute tasks over five times as fast.

The Geekbench Metal test shows a similar story, albeit with a smaller gap. The GTX 1050 Ti scores 7834, which is 182.1% higher than the GT 745M’s 2777. This test is particularly relevant for users in Apple ecosystems, and the data confirms that the GTX 1050 Ti is a far more capable compute device.

The closest contest is in Geekbench Vulkan, where the GTX 1050 Ti scores 10001 and the GT 745M scores 5502. The 81.8% delta is still a landslide, but it is the smallest of the three. This suggests that while the GT 745M’s Vulkan driver implementation is functional, it cannot compensate for the underlying hardware deficit. The GTX 1050 Ti’s support for Vulkan 1.4, versus the GT 745M’s Vulkan 1.2.175, also contributes to its superior showing.

Outside of these three, the GTX 1050 Ti has additional benchmarks not run on the GT 745M. These include a Passmark G3D score of 6340 and a Passmark GPU Compute score of 2652, indicating strong general 3D and compute performance. The GT 745M has no such data points, further limiting its utility in any modern workload assessment.

Specification Differences

The specification sheets for these two GPUs reveal a stark contrast in almost every field. The GTX 1050 Ti is built on a 14 nm process at Samsung, while the GT 745M uses a 28 nm process at TSMC. The GTX 1050 Ti’s GP107 chip contains 3,300 million transistors on a 132 mm² die, versus 1,270 million transistors on a 118 mm² die for the GT 745M’s GK107. This results in a transistor density of 25.0M / mm² for the GTX 1050 Ti, more than double the GT 745M’s 10.8M / mm².

The clock speeds differ, though the GT 745M has no listed base or boost clock. The GTX 1050 Ti runs at 1291 MHz base and 1392 MHz boost, with memory at 1752 MHz (7 Gbps effective). The GT 745M’s memory runs at 1000 MHz (4 Gbps effective). The GTX 1050 Ti has 4 GB of GDDR5 memory versus 2 GB for the GT 745M, both on a 128-bit bus. Consequently, the GTX 1050 Ti’s bandwidth is 112.1 GB/s, nearly double the GT 745M’s 64.00 GB/s.

Compute resources are radically different: the GTX 1050 Ti has 768 shading units, 48 TMUs, and 32 ROPs, while the GT 745M has 384 shading units, 32 TMUs, and 16 ROPs. Pixel and texture rates follow suit: the GTX 1050 Ti achieves 44.54 GPixel/s and 66.82 GTexel/s, versus the GT 745M’s 4.392 GPixel/s and 17.57 GTexel/s. The FP32 throughput is 2.138 TFLOPS for the GTX 1050 Ti and 421.6 GFLOPS for the GT 745M. The GTX 1050 Ti also supports FP16 at 33.41 GFLOPS, a capability absent from the GT 745M.

Power and physical specs diverge as well. The GTX 1050 Ti has a 75 W TDP and is a dual-slot card with no power connectors, requiring a 250 W power supply. The GT 745M has a 45 W TDP and is classified as an IGP with dimensions dependent on the portable device. The GTX 1050 Ti offers display outputs of 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a, while the GT 745M’s outputs are “Portable Device Dependent.” The API support also differs: the GTX 1050 Ti supports DirectX 12 (12_1) and Vulkan 1.4, while the GT 745M only reaches DirectX 12 (11_0) and Vulkan 1.2.175. Both support OpenGL 4.6. The GTX 1050 Ti was released in October 2016 with a launch MSRP of 139 USD, while the GT 745M came out in March 2013 with no listed MSRP.

DETAILED SPECIFICATIONS

SPECIFICATION
GT 745M
GTX 1050 Ti
Core Specs
Shading Units
384
768 +100.0%
Shaders
384
768 +100.0%
TMUs
32
48 +50.0%
ROPs
16
32 +100.0%
SM Count
—
6
Clocks
Base Clock
—
1291 MHz
Boost Clock
—
1392 MHz
GPU Clock
549 MHz
—
Memory Clock
1000 MHz 4 Gbps effective
1752 MHz 7 Gbps effective
Memory
Memory Size
2 GB
4 GB
VRAM (MB)
2,048
4,096 +100.0%
Memory Type
GDDR5
GDDR5
Memory Bus
128 bit
128 bit
Bandwidth
64.00 GB/s
112.1 GB/s
Cache
L1 Cache
16 KB (per SMX)
48 KB (per SM)
L2 Cache
256 KB
1024 KB
Performance
Pixel Rate
4.392 GPixel/s
44.54 GPixel/s
Texture Rate
17.57 GTexel/s
66.82 GTexel/s
FP32 (TFLOPS)
421.6 GFLOPS
2.138 TFLOPS
FP64 (TFLOPS)
17.57 GFLOPS (1:24)
66.82 GFLOPS (1:32)
FP16 (TFLOPS)
—
33.41 GFLOPS (1:64)
Power
TDP
45 W
75 W
TDP (W)
45
75 +66.7%
Suggested PSU
—
250 W
Power Connectors
—
None
Architecture
Architecture
Kepler
Pascal
GPU Name
GK107
GP107
Generation
GeForce 700M
GeForce 10
Process Size
28 nm
14 nm
Transistors
1,270 million
3,300 million
Die Size
118 mm²
132 mm²
Foundry
TSMC
Samsung
Density
10.8M / mm²
25.0M / mm²
API Support
DirectX
12 (11_0)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.2.175
1.4
OpenCL
3.0
3.0
CUDA
3.0
6.1
Shader Model
6.5 (5.1)
6.8
Physical
Slot Width
IGP
Dual-slot
Length
—
145 mm 5.7 inches
Height
—
111 mm 4.4 inches
Outputs
Portable Device Dependent
1x DVI1x HDMI 2.01x DisplayPort 1.4a
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Other
Launch Price
—
139 USD
Production
End-of-life
End-of-life
Predecessor
GeForce 600M
GeForce 900
Successor
GeForce 800M
GeForce 20
View GeForce GT 745M Details View GeForce GTX 1050 Ti Details