AMD Radeon RX 6600S vs NVIDIA RTX PRO 6000D Blackwell Max-Q Comparison

AMD
RADEON

AMD Radeon RX 6600S

CORE STATE Navi 23
VRAM 4 GB
CLOCK SPEED 2000 MHz
TDP 80 W
BUS WIDTH 128 bit
ARCHITECTURE RDNA 2.0
nm
PROCESS 7 nm
LAUNCH DATE 2022
VS
NVIDIA
GEFORCE

RTX PRO 6000D Blackwell Max-Q

CORE STATE GB202
VRAM 96 GB
CLOCK SPEED 2288 MHz
TDP 300 W
BUS WIDTH 512 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

geekbench_opencl
66,435
N/A
passmark_directx_10
81
N/A
passmark_directx_11
105
N/A
passmark_directx_12
56
N/A
passmark_directx_9
176
N/A
passmark_g2d
647
N/A
passmark_g3d
12,649
N/A
passmark_gpu_compute
4,879
N/A
3dmark_3dmark_steel_nomad_dx12
N/A
11,088

Analysis: AMD Radeon RX 6600S vs NVIDIA RTX PRO 6000D Blackwell Max-Q

Head-to-Head Benchmarks

The benchmark data presents an unusual comparison: NVIDIA’s RTX PRO 6000D Blackwell Max-Q and AMD’s Radeon RX 6600S target completely different market segments, and their available test results reflect that divide. The NVIDIA card’s single benchmark entry is 3DMark Steel Nomad DX12, scoring 11,088 points. The AMD card has no 3DMark result, instead offering a broader suite of synthetic tests including Geekbench OpenCL and multiple Passmark variants. Direct head-to-head scores are absent, so the comparison relies on each card’s average benchmark score and its position relative to its own nearest rivals.

The NVIDIA RTX PRO 6000D Blackwell Max-Q posts an average benchmark score of 11,088, placing it at the 50th percentile of all GPUs. Its closest competitor in the data is the NVIDIA RTX PRO 6000 Blackwell Max-Q, which scores identically at 11,088 with a 0% delta. The AMD Radeon RX 550 trails by a mere 0.1% at 11,075, while the GeForce GTX 1650 SUPER is 0.4% behind at 11,047. Interestingly, the AMD FirePro W4300 leads this group by 1.2% with a score of 11,225. This tight clustering suggests the RTX PRO 6000D sits in a performance band where sub-2% differences separate it from much older, lower-tier hardware—a notable outcome for a flagship workstation card.

The AMD Radeon RX 6600S averages 10,629 across its benchmark suite, placing it at the 49th percentile. Its nearest rivals show a similarly narrow spread: the Radeon R9 M275X scores 10,582 (0.4% behind), the GeForce GTX 560 Ti scores 10,690 (0.6% ahead), and the Quadro K2200 leads by 1.2% at 10,761. The RX 550X trails by 1.4% at 10,481. The 4.3% gap between the two cards’ average scores (11,088 vs 10,629) is modest in absolute terms, but the context matters: the NVIDIA part achieves this in a single DX12 workload, while the AMD part’s average blends eight different tests spanning OpenCL, DirectX 9 through 12, and 2D compute.

Breaking down the AMD card’s individual results reveals a wide variance. Its strongest showing is in Geekbench OpenCL at 66,435, a test that heavily favors compute throughput. Passmark G3D scores 12,649, while DirectX 11 and DirectX 9 yield 105 and 176 respectively. DirectX 12 drops to 56, and DirectX 10 sits at 81. The G2D score of 647 and GPU compute score of 4,879 round out the picture. These numbers illustrate that the RX 6600S is not a consistent performer across API generations—its legacy DirectX scores are particularly low relative to its modern compute capability.

Where Each One Wins

The NVIDIA RTX PRO 6000D Blackwell Max-Q wins decisively in raw graphics throughput. Its FP32 compute rating of 110.1 TFLOPS dwarfs the AMD card’s 7.168 TFLOPS, representing a 15.4x advantage. Pixel fill rate favors NVIDIA at 439.3 GPixel/s versus 128.0 GPixel/s, and texture rate shows 1,720.6 GTexel/s against 224.0 GTexel/s. Memory bandwidth is another landslide: 1.79 TB/s versus 224.0 GB/s, an eightfold difference. These specifications translate to workloads where massive data movement and high-resolution rendering dominate—think large scene compositing, scientific visualization, or AI training datasets that exceed 4 GB.

The AMD Radeon RX 6600S wins in efficiency and form factor. Its TDP of 80 W is a fraction of the NVIDIA card’s 300 W, making it suitable for thin-and-light laptops where power budgets are tight. The RX 6600S is an IGP (integrated graphics processor) with no power connectors, while the RTX PRO 6000D requires a dual-slot cooler and a 1x 16-pin connector. The AMD card’s 7 nm process node, while older than NVIDIA’s 5 nm, still delivers functional performance in a package that the NVIDIA card cannot match for portability. In FPGA-style compute tests, the RX 6600S’s Geekbench OpenCL score of 66,435 is its single greatest strength, though this is not directly comparable to the NVIDIA card’s 3DMark result.

Looking at benchmark wins, the NVIDIA card leads in the only shared metric category—modern DX12 performance—while the AMD card’s suite covers a broader range of APIs. The RX 6600S’s Passmark DirectX 9 score of 176 and DirectX 11 score of 105 indicate it handles older titles adequately, but its DirectX 12 score of 56 is weak. The RTX PRO 6000D’s 3DMark Steel Nomad DX12 score of 11,088 suggests strong modern API performance, though no legacy API data exists for it.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. NVIDIA’s RTX PRO 6000D Blackwell Max-Q uses the GB202 chip on TSMC’s 5 nm process, packing 92,200 million transistors into a 750 mm² die. This yields a transistor density of 122.9 million per mm². The architecture is Blackwell 2.0, part of the Blackwell PRO W (x000) generation, released on 2025-03-17. It features 24,064 shading units, 752 TMUs, 192 ROPs, 188 RT cores, and 752 tensor cores. Memory is 96 GB of GDDR7 on a 512-bit bus, with a 1750 MHz memory clock running at 28 Gbps effective.

AMD’s Radeon RX 6600S uses the Navi 23 chip on TSMC’s 7 nm process, with 11,060 million transistors on a 237 mm² die—a density of 46.7 million per mm². The RDNA 2.0 architecture belongs to the Navi Mobile (RX 6000M) generation, released 2022-01-03. It has 1,792 shading units, 112 TMUs, 64 ROPs, and 28 RT cores, with no tensor cores. Memory is 4 GB of GDDR6 on a 128-bit bus, clocked at 1750 MHz with 14 Gbps effective. The FP16 ratio differs: NVIDIA offers 1:1 FP16 to FP32 (110.1 TFLOPS each), while AMD provides 2:1 FP16 (14.34 TFLOPS) versus FP32 (7.168 TFLOPS).

Other differences are practical. NVIDIA’s card uses PCIe 5.0 x16, while AMD uses PCIe 4.0 x8. Display outputs are 4x DisplayPort 2.1b on the NVIDIA card, versus “Portable Device Dependent” on the AMD part. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA card is dual-slot, 267 mm long, 111 mm tall, and 40 mm wide; the AMD card has no listed dimensions, consistent with its mobile IGP nature.

FAQ

Q: Which card has higher raw compute throughput?

A: The NVIDIA RTX PRO 6000D Blackwell Max-Q delivers 110.1 TFLOPS FP32, which is 15.4 times the AMD Radeon RX 6600S’s 7.168 TFLOPS. The NVIDIA card also offers FP16 at the same 110.1 TFLOPS, while the AMD card’s FP16 reaches 14.34 TFLOPS.

Q: How do their memory subsystems compare?

A: NVIDIA provides 96 GB of GDDR7 on a 512-bit bus with 1.79 TB/s bandwidth. AMD provides 4 GB of GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth. The NVIDIA card has 24 times the memory capacity and roughly eight times the bandwidth.

Q: What are the power requirements?

A: The NVIDIA card has a TDP of 300 W and requires a 700 W suggested PSU, using a 1x 16-pin connector. The AMD card has an 80 W TDP, uses no power connectors, and is classified as an IGP with no suggested PSU listed.

Q: Which card is better for modern DirectX 12 workloads?

A: Based on the 3DMark Steel Nomad DX12 test, the NVIDIA card scores 11,088, placing it at the 50th percentile. The AMD card’s Passmark DirectX 12 score is 56, which is its lowest API-specific result, indicating weak modern API performance relative to its other tests.

Q: Are these cards direct competitors in any market?

A: No. The NVIDIA card is a 300 W dual-slot workstation GPU with 96 GB memory, while the AMD card is an 80 W mobile IGP with 4 GB memory. Their nearest rivals in the data are older, lower-tier GPUs, not each other.

Q: What is the production status of each?

A: The NVIDIA RTX PRO 6000D Blackwell Max-Q is listed as Active, with a launch MSRP of 8,565 USD. The AMD Radeon RX 6600S is End-of-life.

Specification Differences

| Specification | NVIDIA RTX PRO 6000D Blackwell Max-Q | AMD Radeon RX 6600S |

|---|---|---|

| Chip | GB202 | Navi 23 |

| Architecture | Blackwell 2.0 | RDNA 2.0 |

| Process Node | 5 nm | 7 nm |

| Transistors | 92,200 million | 11,060 million |

| Die Size | 750 mm² | 237 mm² |

| Transistor Density | 122.9M / mm² | 46.7M / mm² |

| Base Clock | 1590 MHz | 1700 MHz |

| Boost Clock | 2288 MHz | 2000 MHz |

| Game Clock | None | 1881 MHz |

| Memory Size | 96 GB | 4 GB |

| Memory Type | GDDR7 | GDDR6 |

| Memory Bus | 512 bit | 128 bit |

| Memory Bandwidth | 1.79 TB/s | 224.0 GB/s |

| Shading Units | 24,064 | 1,792 |

| TMUs | 752 | 112 |

| ROPs | 192 | 64 |

| RT Cores | 188 | 28 |

| Tensor Cores | 752 | None |

| FP32 Performance | 110.1 TFLOPS | 7.168 TFLOPS |

| FP16 Performance | 110.1 TFLOPS (1:1) | 14.34 TFLOPS (2:1) |

| TDP | 300 W | 80 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 1x 16-pin | None |

| Suggested PSU | 700 W | None |

| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x8 |

| Display Outputs | 4x DisplayPort 2.1b | Portable Device Dependent |

| Dimensions | 267 mm x 111 mm x 40 mm | None listed |

| Production Status | Active | End-of-life |

| Release Date | 2025-03-17 | 2022-01-03 |

| Launch MSRP | 8,565 USD | None |

The Verdict

The data points to two entirely different purchasing decisions. The NVIDIA RTX PRO 6000D Blackwell Max-Q is for professionals who need massive memory capacity and compute throughput. Its 96 GB GDDR7 pool and 110.1 TFLOPS FP32 performance handle workloads that would immediately exhaust the AMD card’s 4 GB frame buffer. The 3DMark Steel Nomad score of 11,088, while only at the 50th percentile, comes in a modern DX12 test and sits within 1.2% of its nearest rivals, suggesting consistent performance in contemporary APIs. The 300 W TDP and dual-slot form factor are acceptable trade-offs for a workstation that stays on a desk.

The AMD Radeon RX 6600S serves a different purpose entirely. Its 80 W TDP and IGP classification make it a fit for portable systems where battery life and thermals trump raw performance. The Geekbench OpenCL score of 66,435 shows capable compute for its class, and the Passmark G3D score of 12,649 indicates playable performance in lighter titles. However, the DirectX 12 score of 56 is a red flag for modern gaming, and the 49th percentile ranking confirms it is not a high-performance part even among its peers.

Choose the NVIDIA card if your work demands 96 GB of memory, 1.79 TB/s bandwidth, or tensor cores for AI acceleration. Choose the AMD card if you need a low-power integrated solution for a mobile device and can work within 4 GB of VRAM. The 15.4x FP32 gap and 24x memory capacity difference make any direct comparison academic—these are tools for different jobs, and the benchmark data reflects that reality.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 6600S
RTX PRO 6000D Blackwell Max-Q
Core Specs
Shading Units
1,792
24,064 +1242.9%
Shaders
1,792
24,064 +1242.9%
TMUs
112
752 +571.4%
ROPs
64
192 +200.0%
Compute Units
28
—
SM Count
—
188
Clocks
Base Clock
1700 MHz
1590 MHz
Boost Clock
2000 MHz
2288 MHz
Game Clock
1881 MHz
—
Memory Clock
1750 MHz 14 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
4 GB
96 GB
VRAM (MB)
4,096
98,304 +2300.0%
Memory Type
GDDR6
GDDR7
Memory Bus
128 bit
512 bit
Bandwidth
224.0 GB/s
1.79 TB/s
Cache
L1 Cache
128 KB per Array
128 KB (per SM)
L2 Cache
2 MB
128 MB
L3 Cache
32 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
128.0 GPixel/s
439.3 GPixel/s
Texture Rate
224.0 GTexel/s
1,720.6 GTexel/s
FP32 (TFLOPS)
7.168 TFLOPS
110.1 TFLOPS
FP64 (TFLOPS)
448.0 GFLOPS (1:16)
1.721 TFLOPS (1:64)
FP16 (TFLOPS)
14.34 TFLOPS (2:1)
110.1 TFLOPS (1:1)
AI/RT
RT Cores
28
188 +571.4%
Tensor Cores
—
752
Power
TDP
80 W
300 W
TDP (W)
80
300 +275.0%
Suggested PSU
—
700 W
Power Connectors
None
1x 16-pin
Architecture
Architecture
RDNA 2.0
Blackwell 2.0
GPU Name
Navi 23
GB202
Generation
Navi Mobile (RX 6000M)
Blackwell PRO W (x000)
Process Size
7 nm
5 nm
Transistors
11,060 million
92,200 million
Die Size
237 mm²
750 mm²
Foundry
TSMC
TSMC
Density
46.7M / 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
IGP
Dual-slot
Length
—
267 mm 10.5 inches
Height
—
111 mm 4.4 inches
Outputs
Portable Device Dependent
4x DisplayPort 2.1b
Bus Interface
PCIe 4.0 x8
PCIe 5.0 x16
Other
Launch Price
—
8,565 USD
Production
End-of-life
Active
Predecessor
Polaris Mobile
Workstation Ada
View Radeon RX 6600S Details View RTX PRO 6000D Blackwell Max-Q Details