NVIDIA GeForce GT 745M vs NVIDIA GeForce GTX 970M 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 970M

CORE STATE GM204
VRAM 6 GB
CLOCK SPEED 1038 MHz
TDP —
BUS WIDTH 192 bit
ARCHITECTURE Maxwell 2.0
nm
PROCESS 28 nm
LAUNCH DATE 2014

PERFORMANCE BENCHMARKS

geekbench_metal
2,777
N/A
geekbench_opencl
3,580
18,946
geekbench_vulkan
5,502
18,292
3dmark_3dmark_steel_nomad_dx12
N/A
472
passmark_directx_10
N/A
28
passmark_directx_11
N/A
42
passmark_directx_12
N/A
24
passmark_directx_9
N/A
99
passmark_g2d
N/A
381
passmark_g3d
N/A
5,704
passmark_gpu_compute
N/A
2,289

Analysis: NVIDIA GeForce GT 745M vs NVIDIA GeForce GTX 970M

Head-to-Head Benchmarks

The recorded data shows a decisive performance gap between the NVIDIA GeForce GTX 970M and the NVIDIA GeForce GT 745M in the two shared benchmark tests. In Geekbench OpenCL, the GTX 970M scores 18,946 points against 3,580 points for the GT 745M, a delta of 429.2% in favor of the GTX 970M. This is not a marginal difference; the GTX 970M delivers more than five times the compute throughput in this workload.

The Geekbench Vulkan result tells a similar story, though with a slightly narrower margin. The GTX 970M posts 18,292 points, while the GT 745M manages 5,502 points. The delta stands at 232.5%, meaning the GTX 970M is roughly three and a half times faster in this API-bound test. Both benchmarks clearly favor the GTX 970M, and the head-to-head tally reflects that with 2 wins for the GTX 970M and 0 for the GT 745M.

When placed against its nearest rivals in the database, the GTX 970M's average benchmark score of 4,628 sits within a tight cluster. It trails the AMD Radeon RX 9060 XT 16 GB and the AMD Radeon R5 M320, both averaging 4,657, by a mere 0.6%. Conversely, it leads the NVIDIA Quadro M3000M (4,621) by 0.2% and the AMD Radeon R5 M230 (4,577) by 1.1%. These are small deltas, indicating that the GTX 970M is competitively positioned within its immediate performance class, despite the massive absolute gap over the GT 745M.

The GT 745M's average benchmark score is 3,953. Its nearest rivals are all within a fraction of a percent: the AMD Radeon R5 M420 (3,956) is 0.1% ahead, the NVIDIA GeForce 830M (3,957) is 0.1% ahead, the NVIDIA Quadro K2000 (3,964) is 0.3% ahead, and the NVIDIA Quadro 2000D (3,930) trails by 0.6%. The GT 745M sits in the lower middle of the database, and its percentile rank of 23 confirms that it outperforms only about a quarter of all recorded GPUs. The GTX 970M, with a percentile of 27, is only slightly better positioned globally, yet its head-to-head dominance over the GT 745M is overwhelming.

Architecture Differences

The two GPUs come from different architectural generations and target different segments. The GTX 970M is built on the GM204 chip using the Maxwell 2.0 architecture, fabricated on a 28 nm process at TSMC. It packs 5,200 million transistors on a 398 mm² die, yielding a transistor density of 13.1M per mm². The GT 745M, in contrast, uses the GK107 chip based on the older Kepler architecture, also on a 28 nm process, but with only 1,270 million transistors on a 118 mm² die, for a density of 10.8M per mm². The GTX 970M has over four times the transistor count and more than three times the die area.

Core configuration differences are stark. The GTX 970M carries 1,280 shading units, 80 texture mapping units, and 48 raster output pipelines. The GT 745M has just 384 shading units, 32 TMUs, and 16 ROPs. That means the GTX 970M has 3.3 times the shading units, 2.5 times the TMUs, and 3 times the ROPs. These ratios translate directly into the compute and fillrate advantages observed in benchmarks.

Clock behavior also separates the two. The GTX 970M lists a base clock of 924 MHz and a boost clock of 1,038 MHz, while the GT 745M has no recorded base or boost clock in the database. Memory clocks differ as well: the GTX 970M runs its GDDR5 at 1,253 MHz with 5 Gbps effective, while the GT 745M runs at 1,000 MHz with 4 Gbps effective. The GTX 970M has 6 GB of GDDR5 on a 192-bit bus, yielding 120.3 GB/s of bandwidth. The GT 745M has 2 GB on a 128-bit bus, yielding 64.00 GB/s. The GTX 970M provides nearly double the memory bandwidth.

Theoretical throughput figures reinforce the gap. The GTX 970M achieves 49.82 GPixel/s pixel fillrate and 83.04 GTexel/s texture fillrate, with FP32 compute at 2.657 TFLOPS. The GT 745M manages only 4.392 GPixel/s, 17.57 GTexel/s, and 421.6 GFLOPS. In every measured throughput category, the GTX 970M is between roughly 4.7 and 11.3 times faster. The GTX 970M also supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, while the GT 745M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The GTX 970M has a more capable feature set for modern API workloads.

Form factor and interface differ as well. The GTX 970M is an MXM Module with an MXM-B (3.0) interface and no power connectors listed, whereas the GT 745M is an integrated graphics processor (IGP) using PCIe 3.0 x16. The GT 745M has a listed TDP of 45 W, while the GTX 970M has no TDP recorded. Both are end-of-life products, with the GTX 970M released on 2014-10-06 and the GT 745M on 2013-03-31. The GTX 970M belongs to the GeForce 900M generation with the GT 745M in the GeForce 700M generation. Their predecessors and successors also differ: the GTX 970M follows the GeForce 800M and leads to GeForce 10 Mobile, while the GT 745M follows the GeForce 600M and leads to GeForce 800M.

Where Each One Wins

The GTX 970M wins in every measurable category where both GPUs have data. In compute-heavy workloads, the OpenCL delta of 429.2% shows that the GTX 970M is in a completely different performance tier. For applications that leverage Vulkan, the 232.5% advantage in Geekbench Vulkan indicates strong API efficiency on the Maxwell 2.0 architecture. The GTX 970M's higher pixel rate, texture rate, and FP32 throughput make it suitable for tasks like real-time rendering, GPU-accelerated compute, and modern game titles with DirectX 12 features.

The GT 745M, by contrast, has no benchmark wins against the GTX 970M. Its only recorded strengths are relative to its own nearest rivals, where it sits within 0.6% of the AMD Radeon R5 M420 and the NVIDIA GeForce 830M. It also holds a slight edge over the NVIDIA Quadro 2000D by 0.6%. However, in absolute terms, the GT 745M is limited to lighter workloads. Its 64.00 GB/s bandwidth and 421.6 GFLOPS are adequate for basic 2D acceleration, legacy DirectX 9 and 10 titles, and low-resolution gaming. Its Kepler architecture and 2 GB memory capacity restrict it to older games or reduced settings in newer ones.

The GTX 970M's 6 GB frame buffer is a practical advantage for larger textures and higher resolutions, and its 192-bit bus provides the bandwidth to feed those assets. The GT 745M's 128-bit bus and 2 GB capacity are suited to less demanding scenarios. For users running productivity applications that use OpenCL, such as video encoding or image processing, the GTX 970M's 18,946 OpenCL score is a clear indicator of its capability. The GT 745M's 3,580 score suggests it would struggle with such tasks.

The Verdict

The data is unambiguous. The NVIDIA GeForce GTX 970M is the superior GPU in every head-to-head comparison recorded in the database. Its OpenCL score is 429.2% higher, its Vulkan score is 232.5% higher, and its theoretical throughput metrics dwarf the GT 745M. The GTX 970M should be chosen by anyone needing a mobile GPU for modern gaming, GPU compute, or DirectX 12 workloads. Its 6 GB memory, higher bandwidth, and higher shading unit count make it viable for medium to high settings in contemporary titles at the time of its release.

The GT 745M is only appropriate for basic use cases. Its 45 W TDP and IGP form factor make it a low-power option for thin-and-light laptops, but its performance ceiling is low. It can handle everyday desktop tasks, light media playback, and older games, but it will not satisfy demanding applications. The GT 745M's percentile of 23 versus the GTX 970M's percentile of 27 shows both are in the lower half of the database, but the GTX 970M is still significantly ahead within that range.

Users should also consider the architectural maturity. The GTX 970M supports DirectX 12 (12_1) and Vulkan 1.4, while the GT 745M only reaches DirectX 12 (11_0) and Vulkan 1.2.175. This means the GTX 970M can handle newer API features and better future-proofing for software that relies on them. The GT 745M is better left to legacy applications. For any workload that stresses the GPU, the GTX 970M is the clear choice. The GT 745M is a fallback for basic needs only.

FAQ

Q: How much faster is the NVIDIA GeForce GTX 970M in OpenCL compute compared to the GT 745M?

A: The GTX 970M scores 18,946 in Geekbench OpenCL, while the GT 745M scores 3,580. This represents a 429.2% advantage for the GTX 970M.

Q: What is the difference in Vulkan performance between the two GPUs?

A: In Geekbench Vulkan, the GTX 970M scores 18,292 and the GT 745M scores 5,502. The GTX 970M leads by 232.5%.

Q: How do their memory configurations compare?

A: The GTX 970M has 6 GB of GDDR5 on a 192-bit bus with 120.3 GB/s bandwidth. The GT 745M has 2 GB of GDDR5 on a 128-bit bus with 64.00 GB/s bandwidth.

Q: Which GPU supports a higher DirectX version?

A: The GTX 970M supports DirectX 12 (12_1), while the GT 745M supports DirectX 12 (11_0). The GTX 970M also supports Vulkan 1.4 versus Vulkan 1.2.175 on the GT 745M.

Q: What are the shading unit counts for each GPU?

A: The GTX 970M has 1,280 shading units, while the GT 745M has 384 shading units. The GTX 970M also has 80 TMUs and 48 ROPs versus 32 TMUs and 16 ROPs on the GT 745M.

Q: Where does each GPU rank globally in the database?

A: The GTX 970M sits at the 27th percentile of all GPUs, and the GT 745M sits at the 23rd percentile. Their average benchmark scores are 4,628 and 3,953, respectively.

DETAILED SPECIFICATIONS

SPECIFICATION
GT 745M
GTX 970M
Core Specs
Shading Units
384
1,280 +233.3%
Shaders
384
1,280 +233.3%
TMUs
32
80 +150.0%
ROPs
16
48 +200.0%
Clocks
Base Clock
—
924 MHz
Boost Clock
—
1038 MHz
GPU Clock
549 MHz
—
Memory Clock
1000 MHz 4 Gbps effective
1253 MHz 5 Gbps effective
Memory
Memory Size
2 GB
6 GB
VRAM (MB)
2,048
6,144 +200.0%
Memory Type
GDDR5
GDDR5
Memory Bus
128 bit
192 bit
Bandwidth
64.00 GB/s
120.3 GB/s
Cache
L1 Cache
16 KB (per SMX)
48 KB (per SMM)
L2 Cache
256 KB
1536 KB
Performance
Pixel Rate
4.392 GPixel/s
49.82 GPixel/s
Texture Rate
17.57 GTexel/s
83.04 GTexel/s
FP32 (TFLOPS)
421.6 GFLOPS
2.657 TFLOPS
FP64 (TFLOPS)
17.57 GFLOPS (1:24)
83.04 GFLOPS (1:32)
Power
TDP
45 W
—
TDP (W)
45
—
Power Connectors
—
None
Architecture
Architecture
Kepler
Maxwell 2.0
GPU Name
GK107
GM204
Generation
GeForce 700M
GeForce 900M
Process Size
28 nm
28 nm
Transistors
1,270 million
5,200 million
Die Size
118 mm²
398 mm²
Foundry
TSMC
TSMC
Density
10.8M / mm²
13.1M / 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
5.2
Shader Model
6.5 (5.1)
6.8
Physical
Slot Width
IGP
MXM Module
Outputs
Portable Device Dependent
Portable Device Dependent
Bus Interface
PCIe 3.0 x16
MXM-B (3.0)
Other
Production
End-of-life
End-of-life
Predecessor
GeForce 600M
GeForce 800M
Successor
GeForce 800M
GeForce 10 Mobile
View GeForce GT 745M Details View GeForce GTX 970M Details