AMD Radeon RX 6750 GRE 12 GB vs NVIDIA CMP 30HX Comparison

AMD
RADEON

AMD Radeon RX 6750 GRE 12 GB

CORE STATE Navi 22
VRAM 12 GB
CLOCK SPEED 2581 MHz
TDP 250 W
BUS WIDTH 192 bit
ARCHITECTURE RDNA 2.0
nm
PROCESS 7 nm
LAUNCH DATE 2023
VS
NVIDIA
GEFORCE

CMP 30HX

CORE STATE TU116
VRAM 6 GB
CLOCK SPEED 1785 MHz
TDP 125 W
BUS WIDTH 192 bit
ARCHITECTURE Turing
nm
PROCESS 12 nm
LAUNCH DATE 2021

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
2,402
N/A
geekbench_vulkan
108,994
62,484
geekbench_opencl
N/A
65,199

Analysis: AMD Radeon RX 6750 GRE 12 GB vs NVIDIA CMP 30HX

The NVIDIA CMP 30HX and AMD Radeon RX 6750 GRE 12 GB represent two very different approaches to GPU design, one tailored for a specific niche and the other for broad consumer use. While the CMP 30HX is an end-of-life mining part with no display outputs, the RX 6750 GRE is an active, fully-featured graphics card. Benchmark data shows a decisive performance gap between them, with the AMD card leading in the available comparative test.

FAQ

Q: Which GPU is faster in the available benchmark?

A: The AMD Radeon RX 6750 GRE 12 GB is significantly faster. In the Geekbench Vulkan test, it scored 108994, while the NVIDIA CMP 30HX scored 62484, a difference of 42.7% in favor of the AMD card.

Q: What is the performance percentile ranking for each GPU?

A: The NVIDIA CMP 30HX sits in the 89th percentile of all GPUs, while the AMD Radeon RX 6750 GRE 12 GB is in the 87th percentile. Despite the AMD card having a lower percentile, its average benchmark score of 55698 is lower than the CMP 30HX's 63842, which is primarily due to the different benchmark suites used for each.

Q: Do these cards have the same memory configuration?

A: No. The NVIDIA CMP 30HX has 6 GB of GDDR6 memory on a 192-bit bus, yielding 336.0 GB/s of bandwidth. The AMD Radeon RX 6750 GRE 12 GB has double the capacity with 12 GB of GDDR6 memory, also on a 192-bit bus, but with higher bandwidth at 432.0 GB/s.

Q: What are the power requirements for each card?

A: The NVIDIA CMP 30HX has a TDP of 125 W and requires a 300 W power supply with a single 8-pin connector. The AMD Radeon RX 6750 GRE 12 GB has a much higher TDP of 250 W, needs a 600 W power supply, and uses one 6-pin and one 8-pin connector.

Q: Can the NVIDIA CMP 30HX be used for display output?

A: No, the NVIDIA CMP 30HX has no display outputs. It is designed solely for computational tasks like mining. In contrast, the AMD Radeon RX 6750 GRE 12 GB features 1x HDMI 2.1 and 3x DisplayPort 1.4a outputs.

Q: Which card is more recent?

A: The AMD Radeon RX 6750 GRE 12 GB is more recent, with a release date of 2023-10-16, while the NVIDIA CMP 30HX was released on 2021-02-24.

Architecture Differences

The architectural gap between these two GPUs is vast, reflecting their different release dates and intended purposes. The NVIDIA CMP 30HX is built on the Turing architecture using the TU116 chip, fabricated on a 12 nm process at TSMC. This chip contains 6,600 million transistors on a die size of 284 mm², resulting in a transistor density of 23.2M per mm². Turing is a mature architecture that, in this implementation, does not include dedicated ray tracing or tensor cores.

The AMD Radeon RX 6750 GRE 12 GB, on the other hand, is a much newer and more complex design. It uses the RDNA 2.0 architecture with the Navi 22 chip, built on a more advanced 7 nm process, also at TSMC. This allows for a significantly higher transistor count of 17,200 million on a 335 mm² die, giving a transistor density of 51.3M per mm², more than double that of the NVIDIA chip. The RDNA 2.0 architecture includes 40 dedicated ray tracing cores and supports DirectX 12 Ultimate, representing a major generational leap in features and efficiency.

The impact of these differences is clear in the raw compute capabilities. The AMD card has 2,560 shading units, 160 texture mapping units (TMUs), and 64 render output units (ROPs), while the NVIDIA card has 1,408 shading units, 88 TMUs, and 48 ROPs. This leads to a substantial advantage for the AMD card in pixel rate (165.2 GPixel/s vs 85.68 GPixel/s) and texture rate (413.0 GTexel/s vs 157.1 GTexel/s). The FP32 performance also reflects this, with the RX 6750 GRE achieving 13.21 TFLOPS compared to the CMP 30HX's 5.027 TFLOPS.

Head-to-Head Benchmarks

The only directly comparable benchmark in the data is the Geekbench Vulkan test, and it tells a clear story of generational dominance. The AMD Radeon RX 6750 GRE 12 GB scores 108994, while the NVIDIA CMP 30HX scores 62484. This represents a 42.7% advantage for the AMD card, a massive margin that highlights the performance gap between a 2021 mining-specific part and a 2023 consumer gaming GPU.

This single result is the only head-to-head win recorded, with the AMD card taking 1 win and the NVIDIA card taking 0. The sheer scale of the victory is more telling than the win count itself. A 42.7% delta in a synthetic API test like Vulkan often translates to an even larger difference in real-world gaming workloads, where the AMD card's superior texture fill rate and memory bandwidth would be heavily utilized.

While other benchmark scores exist for each card individually, they are not directly comparable. The NVIDIA CMP 30HX has a Geekbench OpenCL score of 65199, while the AMD card has a 3DMark Steel Nomad DX12 score of 2402. These different test suites measure different aspects of performance, so they cannot be used to draw direct conclusions against each other. However, the average benchmark scores for each card, 63842 for the CMP 30HX and 55698 for the RX 6750 GRE, reflect that the AMD card's average is dragged down by the inclusion of its lower Steel Nomad score, while the NVIDIA card's average is based only on its two Geekbench scores.

Specification Differences

The specifications of these two cards diverge on nearly every major point, with only a few similarities like the memory bus width and dual-slot design.

  • Process Node: The NVIDIA CMP 30HX uses a 12 nm process, while the AMD Radeon RX 6750 GRE 12 GB uses a 7 nm process.
  • Transistors: The NVIDIA chip has 6,600 million transistors, while the AMD chip has 17,200 million.
  • Die Size: The NVIDIA die is 284 mm², while the AMD die is 335 mm².
  • Transistor Density: The NVIDIA chip has a density of 23.2M / mm², while the AMD chip has 51.3M / mm².
  • Base Clock: The NVIDIA card has a base clock of 1530 MHz, while the AMD card has a base clock of 2321 MHz.
  • Boost Clock: The NVIDIA card boosts to 1785 MHz, while the AMD card boosts to 2581 MHz.
  • Memory Size: The NVIDIA card has 6 GB of memory, while the AMD card has 12 GB.
  • Memory Clock: The NVIDIA memory runs at 1750 MHz (14 Gbps effective), while the AMD memory runs at 2250 MHz (18 Gbps effective).
  • Memory Bandwidth: The NVIDIA card offers 336.0 GB/s, while the AMD card offers 432.0 GB/s.
  • Shading Units: The NVIDIA card has 1,408, while the AMD card has 2,560.
  • TMUs: The NVIDIA card has 88, while the AMD card has 160.
  • ROPs: The NVIDIA card has 48, while the AMD card has 64.
  • RT Cores: The NVIDIA card has none, while the AMD card has 40.
  • Pixel Rate: The NVIDIA card has 85.68 GPixel/s, while the AMD card has 165.2 GPixel/s.
  • Texture Rate: The NVIDIA card has 157.1 GTexel/s, while the AMD card has 413.0 GTexel/s.
  • FP32 Performance: The NVIDIA card has 5.027 TFLOPS, while the AMD card has 13.21 TFLOPS.
  • TDP: The NVIDIA card has a TDP of 125 W, while the AMD card has a TDP of 250 W.
  • Power Connectors: The NVIDIA card uses 1x 8-pin, while the AMD card uses 1x 6-pin + 1x 8-pin.
  • Suggested PSU: The NVIDIA card requires a 300 W PSU, while the AMD card requires a 600 W PSU.
  • Bus Interface: The NVIDIA card uses PCIe 1.0 x4, while the AMD card uses PCIe 4.0 x16.
  • Display Outputs: The NVIDIA card has no outputs, while the AMD card has 1x HDMI 2.1 and 3x DisplayPort 1.4a.
  • DirectX Support: The NVIDIA card supports DirectX 12 (12_1), while the AMD card supports DirectX 12 Ultimate (12_2).
  • Dimensions: The NVIDIA card is 229 mm long, while the AMD card is 267 mm long. The NVIDIA card is 111 mm high and 35 mm wide, while the AMD card is 110 mm high and 40 mm wide.
  • Release Date: The NVIDIA card was released on 2021-02-24, while the AMD card was released on 2023-10-16.
  • Production Status: The NVIDIA card is end-of-life, while the AMD card is active.

Where Each One Wins

The AMD Radeon RX 6750 GRE 12 GB is the clear winner for any use case that requires graphics output, modern features, or raw performance. Its 42.7% lead in the Vulkan benchmark, combined with its double memory capacity, higher bandwidth, and dedicated ray tracing cores, makes it the only sensible choice for gaming, content creation, or any general-purpose GPU workload. The 12 GB of VRAM is a significant advantage for modern games and professional applications that are increasingly memory-hungry.

The NVIDIA CMP 30HX has no wins in the head-to-head data and is fundamentally a niche product. Its strengths lie in its low power consumption, with a 125 W TDP that is half that of the AMD card, and its compact 229 mm length. However, these advantages are irrelevant for most users because the card has no display outputs. Its only potential use case is in a dedicated compute or mining rig where display output is unnecessary and low power draw is a priority. Even then, its significantly lower compute performance makes it a poor choice compared to the AMD card, which offers over double the FP32 throughput. The data clearly shows that the AMD Radeon RX 6750 GRE 12 GB is the superior product in nearly every measurable way.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 6750 GRE 12 GB
CMP 30HX
Core Specs
Shading Units
2,560
1,408 -45.0%
Shaders
2,560
1,408 -45.0%
TMUs
160
88 -45.0%
ROPs
64
48 -25.0%
Compute Units
40
—
SM Count
—
22
Clocks
Base Clock
2321 MHz
1530 MHz
Boost Clock
2581 MHz
1785 MHz
Game Clock
2439 MHz
—
Memory Clock
2250 MHz 18 Gbps effective
1750 MHz 14 Gbps effective
Memory
Memory Size
12 GB
6 GB
VRAM (MB)
12,288
6,144 -50.0%
Memory Type
GDDR6
GDDR6
Memory Bus
192 bit
192 bit
Bandwidth
432.0 GB/s
336.0 GB/s
Cache
L1 Cache
128 KB per Array
64 KB (per SM)
L2 Cache
3 MB
1536 KB
L3 Cache
96 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
165.2 GPixel/s
85.68 GPixel/s
Texture Rate
413.0 GTexel/s
157.1 GTexel/s
FP32 (TFLOPS)
13.21 TFLOPS
5.027 TFLOPS
FP64 (TFLOPS)
825.9 GFLOPS (1:16)
157.1 GFLOPS (1:32)
FP16 (TFLOPS)
26.43 TFLOPS (2:1)
10.05 TFLOPS (2:1)
AI/RT
RT Cores
40
—
Power
TDP
250 W
125 W
TDP (W)
250
125 -50.0%
Suggested PSU
600 W
300 W
Power Connectors
1x 6-pin + 1x 8-pin
1x 8-pin
Architecture
Architecture
RDNA 2.0
Turing
GPU Name
Navi 22
TU116
Generation
Navi II (RX 6000)
Mining GPUs
Process Size
7 nm
12 nm
Transistors
17,200 million
6,600 million
Die Size
335 mm²
284 mm²
Foundry
TSMC
TSMC
Density
51.3M / mm²
23.2M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.1
3.0
CUDA
—
7.5
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm 10.5 inches
229 mm 9 inches
Height
110 mm 4.3 inches
111 mm 4.4 inches
Outputs
1x HDMI 2.13x DisplayPort 1.4a
No outputs
Bus Interface
PCIe 4.0 x16
PCIe 1.0 x4
Other
Launch Price
334 USD
799 USD
Production
Active
End-of-life
Predecessor
Navi
—
Successor
Navi III
—
View Radeon RX 6750 GRE 12 GB Details View CMP 30HX Details