AMD Radeon RX 6750 GRE 10 GB vs NVIDIA GeForce RTX 5090 SE Comparison

AMD
RADEON

AMD Radeon RX 6750 GRE 10 GB

CORE STATE Navi 22
VRAM 10 GB
CLOCK SPEED 2450 MHz
TDP 170 W
BUS WIDTH 160 bit
ARCHITECTURE RDNA 2.0
nm
PROCESS 7 nm
LAUNCH DATE 2023
VS
NVIDIA
GEFORCE

GeForce RTX 5090 SE

CORE STATE GB202
VRAM 24 GB
CLOCK SPEED 2377 MHz
TDP 500 W
BUS WIDTH 384 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
1,995
N/A

Analysis: AMD Radeon RX 6750 GRE 10 GB vs NVIDIA GeForce RTX 5090 SE

The Verdict

The data places these two GPUs in entirely different competitive classes. The AMD Radeon RX 6750 GRE 10 GB is a mid-range RDNA 2.0 part that, based on its recorded benchmark score, sits near the 13th percentile of all GPUs in the database. The NVIDIA GeForce RTX 5090 SE is a flagship Blackwell 2.0 part with a 50th percentile ranking, though its average benchmark score is recorded as zero due to a lack of test data. The pick is straightforward: the RTX 5090 SE is the high-end choice for maximum compute throughput, while the RX 6750 GRE serves as the lower-tier option with a proven, if modest, performance score.

For users prioritizing raw processing power, the RTX 5090 SE is the clear selection. It carries 14,080 shading units, 440 texture mapping units, 160 render output units, 110 RT cores, and 440 tensor cores. Its FP32 throughput is 66.94 TFLOPS, and its texture rate is 1,045.9 GTexel/s. The RX 6750 GRE offers 2,304 shading units, 144 TMUs, 64 ROPs, and 36 RT cores, with FP32 at 11.29 TFLOPS and a texture rate of 352.8 GTexel/s. The RTX 5090 SE delivers over five times the FP32 compute and nearly three times the texture rate, a decisive gap.

The RX 6750 GRE is the pick for systems with tighter power delivery constraints. Its TDP is 170 W with a suggested PSU of 450 W and a single 8-pin connector. The RTX 5090 SE requires 500 W, a suggested 900 W PSU, and a 16-pin connector. The benchmark data for the RX 6750 GRE shows a 3DMark Steel Nomad DX12 score of 1,995, placing it 1% ahead of the NVIDIA GRID K1 and 1.1% ahead of the GeForce GTX 470, while sitting 1.6% behind the Intel UHD Graphics 770. The RTX 5090 SE has no recorded benchmark scores, so its performance must be inferred from its specifications alone.

FAQ

Q: Which GPU has the higher recorded benchmark score?

A: The AMD Radeon RX 6750 GRE 10 GB has a recorded 3DMark Steel Nomad DX12 score of 1,995. The NVIDIA GeForce RTX 5090 SE has no recorded benchmark scores in the database, with an average benchmark score of zero.

Q: How does the RX 6750 GRE compare to its nearest rivals?

A: The RX 6750 GRE is 1% ahead of the NVIDIA GRID K1 and 1.1% ahead of the GeForce GTX 470. It trails the Intel UHD Graphics 770 by 1.6% and the GeForce GTX 660M by 1.7%.

Q: What are the memory specifications of each card?

A: The RX 6750 GRE uses 10 GB of GDDR6 on a 160-bit bus with 320.0 GB/s bandwidth. The RTX 5090 SE uses 24 GB of GDDR7 on a 384-bit bus with 1.34 TB/s bandwidth.

Q: Which card has a higher transistor density?

A: The RTX 5090 SE has a transistor density of 122.9M per mm², based on 92,200 million transistors on a 750 mm² die. The RX 6750 GRE has a density of 51.3M per mm², with 17,200 million transistors on a 335 mm² die.

Q: Do both cards support the same DirectX version?

A: Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 5090 SE adds tensor cores, which the RX 6750 GRE lacks.

Q: What is the launch MSRP of each card?

A: The AMD Radeon RX 6750 GRE 10 GB has a launch MSRP of 309 USD. The NVIDIA GeForce RTX 5090 SE has a launch MSRP of 1,499 USD.

Architecture Differences

The two GPUs come from different architectural generations. The AMD part uses RDNA 2.0, built on the Navi 22 chip at a 7 nm process node from TSMC. It belongs to the Navi II (RX 6000) generation. The NVIDIA part uses Blackwell 2.0, built on the GB202 chip at a 5 nm process node, also from TSMC, and belongs to the GeForce 50 generation.

Transistor counts differ substantially. The RX 6750 GRE integrates 17,200 million transistors on a 335 mm² die, yielding a density of 51.3M per mm². The RTX 5090 SE integrates 92,200 million transistors on a 750 mm² die, yielding a density of 122.9M per mm². The newer process and larger die give the NVIDIA card a density advantage of roughly 2.4 times.

The RTX 5090 SE includes dedicated tensor cores, 440 of them, which the RX 6750 GRE does not have. RT core counts also differ: the NVIDIA card has 110 RT cores versus 36 on the AMD card. The shading unit count scales accordingly: 14,080 on the RTX 5090 SE versus 2,304 on the RX 6750 GRE. The AMD card uses a 2:1 FP16 to FP32 ratio, delivering 22.58 TFLOPS FP16 against 11.29 TFLOPS FP32. The NVIDIA card uses a 1:1 ratio, with 66.94 TFLOPS for both FP16 and FP32.

Specification Differences

Clock speeds vary. The RX 6750 GRE has a base clock of 1,941 MHz, a boost clock of 2,450 MHz, and a game clock of 2,189 MHz. The RTX 5090 SE has a base clock of 1,740 MHz and a boost clock of 2,377 MHz, with no game clock listed. Memory clocks also differ: the AMD card runs at 2,000 MHz with 16 Gbps effective, while the NVIDIA card runs at 1,750 MHz with 28 Gbps effective.

Memory configuration is a major split. The RX 6750 GRE has 10 GB of GDDR6 on a 160-bit bus, giving 320.0 GB/s bandwidth. The RTX 5090 SE has 24 GB of GDDR7 on a 384-bit bus, giving 1.34 TB/s bandwidth. The NVIDIA card offers 4.2 times the bandwidth and 2.4 times the capacity.

Power requirements are far apart. The RX 6750 GRE has a TDP of 170 W, a suggested PSU of 450 W, and uses a single 8-pin connector. The RTX 5090 SE has a TDP of 500 W, a suggested PSU of 900 W, and uses a single 16-pin connector. Both are dual-slot cards with similar dimensions: the RX 6750 GRE is 267 mm long, 110 mm high, and 40 mm wide; the RTX 5090 SE is 267 mm long, 111 mm high, and 40 mm wide.

Bus interfaces differ. The RX 6750 GRE uses PCIe 4.0 x16, while the RTX 5090 SE uses PCIe 5.0 x16. Display outputs are similar in count but differ in version: the AMD card has 1x HDMI 2.1 and 3x DisplayPort 1.4a, while the NVIDIA card has 1x HDMI 2.1b and 3x DisplayPort 2.1b. Release dates are also different: the RX 6750 GRE was released on 2023-10-16, and the RTX 5090 SE on 2025-12-31.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between these two cards. The RTX 5090 SE has an empty benchmark array, and the head-to-head array is also empty. As a result, a direct comparison of measured performance is not possible. The only recorded score comes from the RX 6750 GRE, which posted 1,995 in 3DMark Steel Nomad DX12.

That score places the RX 6750 GRE at the 13th percentile of all GPUs. Its nearest rivals include the NVIDIA GRID K1 at 1,976 (1% slower), the GeForce GTX 470 at 1,973 (1.1% slower), the Intel UHD Graphics 770 at 2,027 (1.6% faster), and the GeForce GTX 660M at 2,029 (1.7% faster). These deltas indicate that the RX 6750 GRE sits in a dense performance cluster where small percentage differences separate it from older or integrated parts.

For the RTX 5090 SE, the percentile ranking is 50th, but the average benchmark score is zero, meaning the ranking is based on specifications rather than measured results. With no scores recorded, any performance comparison to the RX 6750 GRE must rely on the specification sheet. The FP32 throughput difference is 55.65 TFLOPS in favor of the RTX 5090 SE, and the texture rate difference is 693.1 GTexel/s in the same direction. The pixel rate also favors the NVIDIA card: 380.3 GPixel/s versus 156.8 GPixel/s.

Where Each One Wins

The RX 6750 GRE wins in power efficiency. Its 170 W TDP and 450 W suggested PSU make it suitable for systems with modest power budgets. The RTX 5090 SE demands 500 W and a 900 W PSU, more than doubling the power requirement. The AMD card also uses a standard 8-pin connector, while the NVIDIA card requires a 16-pin connector.

The RX 6750 GRE wins in the measured benchmark category. It has a recorded 3DMark Steel Nomad DX12 score of 1,995, while the RTX 5090 SE has no recorded scores. For any database comparison based on actual test results, the AMD card is the only one with data.

The RTX 5090 SE wins in raw compute throughput. Its 66.94 TFLOPS FP32 is 5.9 times the RX 6750 GRE's 11.29 TFLOPS. Its texture rate of 1,045.9 GTexel/s is 2.96 times higher, and its pixel rate of 380.3 GPixel/s is 2.42 times higher. The NVIDIA card also has more shading units, TMUs, ROPs, RT cores, and adds tensor cores entirely absent from the AMD part.

The RTX 5090 SE wins in memory performance. Its 1.34 TB/s bandwidth is 4.19 times the 320.0 GB/s of the RX 6750 GRE. It also has 24 GB of GDDR7 memory versus 10 GB of GDDR6, a 14 GB capacity advantage. The 384-bit bus is 2.4 times wider than the 160-bit bus on the AMD card.

The RTX 5090 SE wins in interface and display connectivity. It uses PCIe 5.0 x16 versus PCIe 4.0 x16, and its DisplayPort 2.1b outputs are newer than the DisplayPort 1.4a on the RX 6750 GRE. The HDMI version is also newer on the NVIDIA card: 2.1b versus 2.1.

The RTX 5090 SE wins in transistor density and architecture features. Its 122.9M per mm² density compares to 51.3M per mm², and its Blackwell 2.0 architecture provides a 1:1 FP16 to FP32 ratio, whereas RDNA 2.0 uses a 2:1 ratio. The tensor core count of 440 is a feature the RX 6750 GRE cannot match.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 6750 GRE 10 GB
RTX 5090 SE
Core Specs
Shading Units
2,304
14,080 +511.1%
Shaders
2,304
14,080 +511.1%
TMUs
144
440 +205.6%
ROPs
64
160 +150.0%
Compute Units
36
—
SM Count
—
110
Clocks
Base Clock
1941 MHz
1740 MHz
Boost Clock
2450 MHz
2377 MHz
Game Clock
2189 MHz
—
Memory Clock
2000 MHz 16 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
10 GB
24 GB
VRAM (MB)
10,240
24,576 +140.0%
Memory Type
GDDR6
GDDR7
Memory Bus
160 bit
384 bit
Bandwidth
320.0 GB/s
1.34 TB/s
Cache
L1 Cache
128 KB per Array
128 KB (per SM)
L2 Cache
3 MB
96 MB
L3 Cache
80 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
156.8 GPixel/s
380.3 GPixel/s
Texture Rate
352.8 GTexel/s
1,045.9 GTexel/s
FP32 (TFLOPS)
11.29 TFLOPS
66.94 TFLOPS
FP64 (TFLOPS)
705.6 GFLOPS (1:16)
1,045.9 GFLOPS (1:64)
FP16 (TFLOPS)
22.58 TFLOPS (2:1)
66.94 TFLOPS (1:1)
AI/RT
RT Cores
36
110 +205.6%
Tensor Cores
—
440
Power
TDP
170 W
500 W
TDP (W)
170
500 +194.1%
Suggested PSU
450 W
900 W
Power Connectors
1x 8-pin
1x 16-pin
Architecture
Architecture
RDNA 2.0
Blackwell 2.0
GPU Name
Navi 22
GB202
Generation
Navi II (RX 6000)
GeForce 50
Process Size
7 nm
5 nm
Transistors
17,200 million
92,200 million
Die Size
335 mm²
750 mm²
Foundry
TSMC
TSMC
Density
51.3M / mm²
122.9M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.1
3.0
CUDA
—
12.0
Shader Model
6.8
6.9
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm 10.5 inches
267 mm 10.5 inches
Height
110 mm 4.3 inches
111 mm 4.4 inches
Outputs
1x HDMI 2.13x DisplayPort 1.4a
1x HDMI 2.1b3x DisplayPort 2.1b
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Other
Launch Price
309 USD
1,499 USD
Production
Active
Active
Predecessor
Navi
GeForce 40
Successor
Navi III
GeForce 60
View Radeon RX 6750 GRE 10 GB Details View GeForce RTX 5090 SE Details