NVIDIA GeForce GT 745M vs NVIDIA GeForce RTX 4070 GDDR6 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 RTX 4070 GDDR6

CORE STATE AD104
VRAM 12 GB
CLOCK SPEED 2475 MHz
TDP 200 W
BUS WIDTH 192 bit
ARCHITECTURE Ada Lovelace
nm
PROCESS 5 nm
LAUNCH DATE 2024

PERFORMANCE BENCHMARKS

geekbench_metal
2,777
N/A
geekbench_opencl
3,580
N/A
geekbench_vulkan
5,502
N/A
3dmark_3dmark_steel_nomad_dx12
N/A
4,334.5

Analysis: NVIDIA GeForce GT 745M vs NVIDIA GeForce RTX 4070 GDDR6

The NVIDIA GeForce RTX 4070 GDDR6 and the NVIDIA GeForce GT 745M represent two vastly different eras of mobile and desktop graphics. The RTX 4070 GDDR6 is a modern desktop part built on the Ada Lovelace architecture, while the GT 745M is an older Kepler-based mobile GPU. Benchmark data shows a significant performance gulf between them, but each occupies a distinct niche in the hardware landscape.

FAQ

Q: How do the two GPUs compare in terms of raw benchmark scores?

A: The RTX 4070 GDDR6 has an average benchmark score of 4335, while the GT 745M scores 3953. This indicates the RTX 4070 GDDR6 is roughly 9.7% faster on average, though the specific benchmark workloads differ between the two cards.

Q: What is the architectural generation gap between these products?

A: The RTX 4070 GDDR6 is built on the Ada Lovelace architecture using a 5 nm process at TSMC, whereas the GT 745M uses the older Kepler architecture on a 28 nm process. This represents a significant generational leap in manufacturing technology.

Q: Which GPU has more memory and bandwidth?

A: The RTX 4070 GDDR6 features 12 GB of GDDR6 memory on a 192-bit bus, delivering 480.0 GB/s of bandwidth. The GT 745M has 2 GB of GDDR5 memory on a 128-bit bus, providing just 64.00 GB/s.

Q: Are both GPUs still in production?

A: No. Both products are listed as end-of-life. The RTX 4070 GDDR6 was released in August 2024, while the GT 745M launched in March 2013.

Q: What is the transistor count difference between the two chips?

A: The RTX 4070 GDDR6 uses the AD104 chip with 35,800 million transistors on a 294 mm² die. The GT 745M uses the GK107 chip with 1,270 million transistors on a smaller 118 mm² die.

Q: Which GPU supports newer DirectX features?

A: The RTX 4070 GDDR6 supports DirectX 12 Ultimate (12_2), while the GT 745M only supports DirectX 12 (11_0). The RTX 4070 GDDR6 also has Vulkan 1.4 support compared to Vulkan 1.2.175 on the older card.

Architecture Differences

The RTX 4070 GDDR6 is built on NVIDIA's Ada Lovelace architecture, manufactured on a 5 nm process at TSMC. This represents a massive leap over the GT 745M's Kepler architecture, which uses a 28 nm process. The process node shrink allows the AD104 chip to pack 35,800 million transistors into a 294 mm² die, achieving a transistor density of 121.8M per mm². In contrast, the GK107 chip in the GT 745M contains only 1,270 million transistors across a 118 mm² die, with a density of just 10.8M per mm².

The RTX 4070 GDDR6 features dedicated ray tracing cores (46 of them) and tensor cores (184), none of which exist on the GT 745M. These hardware units enable advanced features like real-time ray tracing and AI-accelerated workloads that are simply impossible on the older Kepler part. The shading unit count also differs dramatically, with the RTX 4070 GDDR6 sporting 5,888 shading units versus 384 on the GT 745M.

Memory architecture is another fundamental difference. The RTX 4070 GDDR6 uses 12 GB of GDDR6 memory on a 192-bit bus, while the GT 745M has 2 GB of GDDR5 on a 128-bit bus. The newer card's memory runs at 2500 MHz (20 Gbps effective), compared to 1000 MHz (4 Gbps effective) on the older part. This translates to 480.0 GB/s of bandwidth on the RTX 4070 GDDR6 versus 64.00 GB/s on the GT 745M.

Head-to-Head Benchmarks

Direct head-to-head benchmark comparisons are not available in the data, but the aggregate scores tell a clear story. The RTX 4070 GDDR6 achieves an average benchmark score of 4335, placing it in the 25th percentile of all GPUs. The GT 745M averages 3953, sitting in the 23rd percentile. While these percentile rankings are close, the raw scores show the RTX 4070 GDDR6 holds a lead of roughly 382 points.

The RTX 4070 GDDR6's nearest rivals in the database include the Intel Iris Pro Graphics 5200 (4360, -0.6% delta) and the AMD FirePro W2100 (4295, +0.9% delta). This puts the RTX 4070 GDDR6 in a tight cluster of similarly-performing GPUs, despite its modern architecture. Meanwhile, the GT 745M's nearest rivals include the AMD Radeon R5 M420 (3956, -0.1% delta) and the NVIDIA GeForce 830M (3957, -0.1% delta), showing it performs in line with low-end mobile GPUs from its era.

The GT 745M has individual benchmark results across three tests: Geekbench Metal (2777), Geekbench OpenCL (3580), and Geekbench Vulkan (5502). These show a wide variance depending on the API, with Vulkan performance being notably higher than Metal. The RTX 4070 GDDR6 only has a single benchmark result from 3DMark Steel Nomad DX12, scoring 4334.5.

Specification Differences

The two GPUs differ across nearly every specification category. The RTX 4070 GDDR6 has a base clock of 1920 MHz and a boost clock of 2475 MHz, while the GT 745M does not list base or boost clocks. The RTX 4070 GDDR6 offers 184 texture mapping units and 64 ROPs, compared to 32 TMUs and 16 ROPs on the GT 745M.

Pixel and texture rates show the performance gap clearly. The RTX 4070 GDDR6 achieves 158.4 GPixel/s and 455.4 GTexel/s, while the GT 745M manages only 4.392 GPixel/s and 17.57 GTexel/s. Floating-point performance is similarly lopsided: 29.15 TFLOPS FP32 on the RTX 4070 GDDR6 versus 421.6 GFLOPS FP32 on the GT 745M.

Power requirements differ significantly. The RTX 4070 GDDR6 has a TDP of 200 W and requires a 550 W suggested PSU, using a single 16-pin power connector. The GT 745M is an IGP (integrated graphics processor) with a 45 W TDP and no power connectors or suggested PSU listed. The RTX 4070 GDDR6 is a dual-slot card measuring 240 mm in length, while the GT 745M has no dimensions listed as it is portable-device dependent.

The RTX 4070 GDDR6 uses a PCIe 4.0 x16 interface and offers 1x HDMI 2.1 plus 3x DisplayPort 1.4a outputs. The GT 745M uses PCIe 3.0 x16 and has portable-device-dependent display outputs. The RTX 4070 GDDR6 also supports FP16 at 29.15 TFLOPS (1:1 ratio), while the GT 745M has no FP16 data available.

Where Each One Wins

The RTX 4070 GDDR6 wins decisively in nearly every performance category. Its 12 GB of GDDR6 memory with 480.0 GB/s bandwidth makes it suitable for modern gaming at high resolutions and detail settings. The 46 ray tracing cores and 184 tensor cores enable hardware-accelerated ray tracing and DLSS-style AI upscaling, features entirely absent on the GT 745M. The 29.15 TFLOPS FP32 performance and 455.4 GTexel/s texture rate position it for demanding 3D workloads and content creation tasks.

The RTX 4070 GDDR6's newer API support, including DirectX 12 Ultimate and Vulkan 1.4, ensures compatibility with the latest game engines and graphics features. Its desktop form factor with multiple display outputs makes it suitable for multi-monitor setups and high-refresh-rate gaming. The 200 W TDP, while substantial, is reasonable for a modern high-performance desktop GPU.

The GT 745M wins in the efficiency and portability categories. With a 45 W TDP and IGP form factor, it is designed for thin and light laptops where power consumption and heat are critical constraints. Its 2 GB of GDDR5 memory is adequate for basic tasks like video playback, light photo editing, and older games at modest settings. The GT 745M's 421.6 GFLOPS FP32 performance is sufficient for everyday computing and casual gaming.

The GT 745M also wins on compatibility with older systems, supporting PCIe 3.0 which is backward compatible with a wide range of laptops from its era. Its Vulkan 1.2.175 support, while older than the RTX 4070 GDDR6's Vulkan 1.4, still enables modern graphics APIs in supported applications. For users with legacy software or older operating systems, the GT 745M's simpler feature set may actually be an advantage, as it requires no special drivers or power management beyond what standard laptop platforms provide.

In terms of benchmark percentile rankings, the two GPUs are closer than their specifications suggest. The RTX 4070 GDDR6 sits at the 25th percentile and the GT 745M at the 23rd percentile, meaning both are in the lower half of all GPUs tracked. This reflects the fact that the RTX 4070 GDDR6, despite its modern architecture, is positioned as a mid-range card in the current market, while the GT 745M was a low-end part even in its day.

DETAILED SPECIFICATIONS

SPECIFICATION
GT 745M
RTX 4070 GDDR6
Core Specs
Shading Units
384
5,888 +1433.3%
Shaders
384
5,888 +1433.3%
TMUs
32
184 +475.0%
ROPs
16
64 +300.0%
SM Count
—
46
Clocks
Base Clock
—
1920 MHz
Boost Clock
—
2475 MHz
GPU Clock
549 MHz
—
Memory Clock
1000 MHz 4 Gbps effective
2500 MHz 20 Gbps effective
Memory
Memory Size
2 GB
12 GB
VRAM (MB)
2,048
12,288 +500.0%
Memory Type
GDDR5
GDDR6
Memory Bus
128 bit
192 bit
Bandwidth
64.00 GB/s
480.0 GB/s
Cache
L1 Cache
16 KB (per SMX)
128 KB (per SM)
L2 Cache
256 KB
36 MB
Performance
Pixel Rate
4.392 GPixel/s
158.4 GPixel/s
Texture Rate
17.57 GTexel/s
455.4 GTexel/s
FP32 (TFLOPS)
421.6 GFLOPS
29.15 TFLOPS
FP64 (TFLOPS)
17.57 GFLOPS (1:24)
455.4 GFLOPS (1:64)
FP16 (TFLOPS)
—
29.15 TFLOPS (1:1)
AI/RT
RT Cores
—
46
Tensor Cores
—
184
Power
TDP
45 W
200 W
TDP (W)
45
200 +344.4%
Suggested PSU
—
550 W
Power Connectors
—
1x 16-pin
Architecture
Architecture
Kepler
Ada Lovelace
GPU Name
GK107
AD104
Generation
GeForce 700M
GeForce 40
Process Size
28 nm
5 nm
Transistors
1,270 million
35,800 million
Die Size
118 mm²
294 mm²
Foundry
TSMC
TSMC
Density
10.8M / mm²
121.8M / mm²
API Support
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.2.175
1.4
OpenCL
3.0
3.0
CUDA
3.0
8.9
Shader Model
6.5 (5.1)
6.9
Physical
Slot Width
IGP
Dual-slot
Length
—
240 mm 9.4 inches
Height
—
110 mm 4.3 inches
Outputs
Portable Device Dependent
1x HDMI 2.13x DisplayPort 1.4a
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Other
Launch Price
—
599 USD
Production
End-of-life
End-of-life
Predecessor
GeForce 600M
GeForce 30
Successor
GeForce 800M
GeForce 50
View GeForce GT 745M Details View GeForce RTX 4070 GDDR6 Details