AMD Radeon RX 6800S vs NVIDIA GeForce RTX 3080 Mobile Comparison

AMD
RADEON

AMD Radeon RX 6800S

CORE STATE Navi 23
VRAM 8 GB
CLOCK SPEED 2100 MHz
TDP 100 W
BUS WIDTH 128 bit
ARCHITECTURE RDNA 2.0
nm
PROCESS 7 nm
LAUNCH DATE 2022
VS
NVIDIA
GEFORCE

GeForce RTX 3080 Mobile

CORE STATE GA104
VRAM 8 GB
CLOCK SPEED 1545 MHz
TDP 115 W
BUS WIDTH 256 bit
ARCHITECTURE Ampere
nm
PROCESS 8 nm
LAUNCH DATE 2021

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
1,689
2,644
geekbench_metal
85,256
N/A
geekbench_opencl
73,202
104,831
geekbench_vulkan
81,272
104,066
passmark_directx_10
91
120
passmark_directx_11
139
146
passmark_directx_12
65
72
passmark_directx_9
200
170
passmark_g2d
732
637
passmark_g3d
15,908
16,321
passmark_gpu_compute
6,144
7,276

Analysis: AMD Radeon RX 6800S vs NVIDIA GeForce RTX 3080 Mobile

The AMD Radeon RX 6800S and NVIDIA GeForce RTX 3080 Mobile are both end-of-life mobile graphics solutions, yet benchmark results show a clear performance hierarchy. Across ten head-to-head tests, the NVIDIA GeForce RTX 3080 Mobile claims eight victories, while the AMD Radeon RX 6800S secures two. The average benchmark scores place the AMD part at 24,063 and the NVIDIA part at 23,628, a difference of less than 2%, but the distribution of wins reveals distinct strengths in specific workloads.

Head-to-Head Benchmarks

The most decisive win for the NVIDIA GeForce RTX 3080 Mobile appears in the 3DMark Steel Nomad DX12 test, where it scores 2,644 against the AMD Radeon RX 6800S's 1,689. This represents a delta of -36.1% for the AMD part, meaning the NVIDIA GPU is roughly 56% faster in this modern, demanding DirectX 12 workload. This is the largest margin in the entire comparison and signals a substantial advantage in high-end rendering scenarios.

The NVIDIA GeForce RTX 3080 Mobile also dominates compute-oriented benchmarks. In Geekbench OpenCL, it scores 104,831 versus 73,202 for the AMD Radeon RX 6800S, a 30.2% deficit for AMD. The Geekbench Vulkan result follows the same pattern, with NVIDIA at 104,066 and AMD at 81,272, a 21.9% gap. PassMark GPU Compute shows NVIDIA ahead at 7,276 against 6,144, a 15.6% margin. These results indicate that the NVIDIA Ampere architecture, with its 6,144 shading units and 192 tensor cores, delivers notably higher throughput in general-purpose and API-accelerated workloads.

In legacy DirectX benchmarks, the NVIDIA part continues its lead, though the margins shrink. PassMark DirectX 10 shows NVIDIA at 120 versus AMD's 91, a 24.2% difference. PassMark DirectX 11 is closer, with NVIDIA scoring 146 against AMD's 139, a 4.8% edge. PassMark DirectX 12 gives NVIDIA a 72-to-65 win, a 9.7% margin. The overall PassMark G3D score, a composite of these tests, lands at 16,321 for NVIDIA and 15,908 for AMD, a modest 2.5% advantage for the RTX 3080 Mobile.

The AMD Radeon RX 6800S wins its two tests by significant margins. In PassMark DirectX 9, it scores 200 against NVIDIA's 170, a 17.6% advantage. This suggests the RDNA 2.0 architecture retains strong performance in older, less complex rendering pipelines. The other AMD victory comes in PassMark G2D, a 2D graphics test, where it scores 732 versus NVIDIA's 637, a 14.9% lead. These wins indicate that while the AMD part trails in modern 3D and compute tasks, it holds an edge in legacy APIs and 2D operations.

The Verdict

The data points to a clear choice for most users: the NVIDIA GeForce RTX 3080 Mobile is the stronger performer in modern gaming and compute tasks. It wins the 3DMark Steel Nomad DX12 test by 36.1%, a critical metric for current and future game titles. Its Vulkan and OpenCL scores, both over 30% higher, also make it the better option for creative applications and GPU-accelerated workflows. The PassMark G3D composite, while close, still favors NVIDIA by 2.5%, confirming a broad but consistent advantage.

The AMD Radeon RX 6800S is not without merit. Its 17.6% win in PassMark DirectX 9 and 14.9% win in PassMark G2D suggest it handles legacy software and 2D interfaces with more efficiency. However, these wins are in less demanding or older workloads. For a user primarily running modern DirectX 12 games or engaging in compute-heavy tasks, the NVIDIA GeForce RTX 3080 Mobile is the superior choice based on benchmark results. The AMD part could be considered for systems prioritizing legacy game compatibility or 2D performance, but it lags in the areas that matter most for contemporary use.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 6800S has an average benchmark score of 24,063, while the NVIDIA GeForce RTX 3080 Mobile has an average of 23,628. The AMD part is slightly ahead by 435 points, roughly 1.8%.

Q: How does the AMD Radeon RX 6800S compare to its nearest rivals?

A: The AMD Radeon RX 6800S sits within 1% of several competitors. It trails the NVIDIA GeForce RTX 2080 SUPER by 0.4% and the NVIDIA GeForce GTX 780 Ti by 0.7%, and it leads the AMD Radeon RX 9070 by 0.8%.

Q: In which benchmark does the NVIDIA GeForce RTX 3080 Mobile show its largest lead?

A: The largest lead for the NVIDIA GeForce RTX 3080 Mobile is in 3DMark Steel Nomad DX12, where it scores 2,644 against the AMD Radeon RX 6800S's 1,689, a delta of -36.1% for the AMD part.

Q: What is the closest benchmark result between the two GPUs?

A: The closest result is in PassMark DirectX 11, where the NVIDIA GeForce RTX 3080 Mobile scores 146 and the AMD Radeon RX 6800S scores 139, a margin of only 4.8%.

Q: Does the AMD Radeon RX 6800S win any benchmark tests?

A: Yes, the AMD Radeon RX 6800S wins two tests: PassMark DirectX 9 with a score of 200 (17.6% ahead) and PassMark G2D with a score of 732 (14.9% ahead).

Q: How do the two GPUs rank in the overall percentile against all GPUs?

A: Both the AMD Radeon RX 6800S and the NVIDIA GeForce RTX 3080 Mobile are in the 69th percentile of all GPUs, placing them at an equivalent tier in the overall performance distribution.

Specification Differences

The two GPUs differ substantially in their core specifications. The AMD Radeon RX 6800S has a base clock of 1800 MHz and a boost clock of 2100 MHz, while the NVIDIA GeForce RTX 3080 Mobile operates at a base clock of 1110 MHz and a boost clock of 1545 MHz. The AMD part has a game clock of 1975 MHz, a feature the NVIDIA part does not list.

Memory configurations diverge as well. Both have 8 GB of GDDR6, but the NVIDIA GeForce RTX 3080 Mobile uses a 256-bit bus width, yielding a bandwidth of 448.0 GB/s, whereas the AMD Radeon RX 6800S uses a 128-bit bus with a bandwidth of 256.0 GB/s. Memory clock speeds also differ, with the AMD part running at 2000 MHz (16 Gbps effective) and the NVIDIA part at 1750 MHz (14 Gbps effective).

The power envelope favors the AMD part, with a TDP of 100 W versus 115 W for the NVIDIA GeForce RTX 3080 Mobile. The bus interface also differs: the AMD Radeon RX 6800S uses PCIe 4.0 x8, while the NVIDIA part uses PCIe 4.0 x16. The transistor count and die size show a significant gap, with the NVIDIA GA104 chip containing 17,400 million transistors on a 392 mm² die, compared to the AMD Navi 23's 11,060 million transistors on a 237 mm² die. Transistor density is similar, at 46.7M / mm² for AMD and 44.4M / mm² for NVIDIA.

Architecture Differences

The architectural divide is fundamental. The AMD Radeon RX 6800S is built on RDNA 2.0 architecture using a 7 nm process at TSMC, while the NVIDIA GeForce RTX 3080 Mobile uses Ampere architecture on an 8 nm process at Samsung. This process difference contributes to the AMD part's lower TDP of 100 W compared to NVIDIA's 115 W.

Compute resources differ sharply. The NVIDIA GeForce RTX 3080 Mobile has 6,144 shading units, 192 texture mapping units, and 96 ROPs. The AMD Radeon RX 6800S has 2,048 shading units, 128 TMUs, and 64 ROPs. Ray tracing cores also favor NVIDIA, with 48 RT cores versus 32 for AMD. The NVIDIA part additionally includes 192 tensor cores, a feature the AMD part does not have. This translates to higher theoretical throughput: the NVIDIA part delivers 18.98 TFLOPS FP32 and 18.98 TFLOPS FP16 (1:1), while the AMD part delivers 8.602 TFLOPS FP32 and 17.20 TFLOPS FP16 (2:1).

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA GeForce RTX 3080 Mobile was released on 2021-01-11, while the AMD Radeon RX 6800S followed on 2022-01-03. The NVIDIA part succeeds the GeForce 20 Mobile generation, and the AMD part succeeds the Polaris Mobile generation.

Where Each One Wins

The NVIDIA GeForce RTX 3080 Mobile is the clear victor in modern 3D gaming and compute. Its 36.1% lead in 3DMark Steel Nomad DX12 makes it the better choice for current DirectX 12 titles and future-proofing. The 30.2% advantage in Geekbench OpenCL and 21.9% lead in Geekbench Vulkan position it strongly for GPU-accelerated applications, including rendering, machine learning, and other compute-heavy tasks. Its 15.6% win in PassMark GPU Compute reinforces this, making it the preferred option for users who rely on general-purpose GPU processing.

The AMD Radeon RX 6800S wins in legacy and 2D contexts. Its 17.6% lead in PassMark DirectX 9 indicates better performance in older games and applications built on that API. The 14.9% win in PassMark G2D suggests smoother 2D interface rendering and desktop compositing. For a user with a library of older titles or a workload that is heavily 2D-based, the AMD part offers a measurable advantage. However, these wins are narrow in scope; the NVIDIA GeForce RTX 3080 Mobile wins the composite PassMark G3D score and dominates in every modern API tested, making it the more versatile and powerful overall choice.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 6800S
RTX 3080 Mobile
Core Specs
Shading Units
2,048
6,144 +200.0%
Shaders
2,048
6,144 +200.0%
TMUs
128
192 +50.0%
ROPs
64
96 +50.0%
Compute Units
32
—
SM Count
—
48
Clocks
Base Clock
1800 MHz
1110 MHz
Boost Clock
2100 MHz
1545 MHz
Game Clock
1975 MHz
—
Memory Clock
2000 MHz 16 Gbps effective
1750 MHz 14 Gbps effective
Memory
Memory Size
8 GB
8 GB
VRAM (MB)
8,192
8,192 0.0%
Memory Type
GDDR6
GDDR6
Memory Bus
128 bit
256 bit
Bandwidth
256.0 GB/s
448.0 GB/s
Cache
L1 Cache
128 KB per Array
128 KB (per SM)
L2 Cache
2 MB
4 MB
L3 Cache
32 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
134.4 GPixel/s
148.3 GPixel/s
Texture Rate
268.8 GTexel/s
296.6 GTexel/s
FP32 (TFLOPS)
8.602 TFLOPS
18.98 TFLOPS
FP64 (TFLOPS)
537.6 GFLOPS (1:16)
296.6 GFLOPS (1:64)
FP16 (TFLOPS)
17.20 TFLOPS (2:1)
18.98 TFLOPS (1:1)
AI/RT
RT Cores
32
48 +50.0%
Tensor Cores
—
192
Power
TDP
100 W
115 W
TDP (W)
100
115 +15.0%
Power Connectors
None
None
Architecture
Architecture
RDNA 2.0
Ampere
GPU Name
Navi 23
GA104
Generation
Navi Mobile (RX 6000M)
GeForce 30 Mobile
Process Size
7 nm
8 nm
Transistors
11,060 million
17,400 million
Die Size
237 mm²
392 mm²
Foundry
TSMC
Samsung
Density
46.7M / mm²
44.4M / 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
—
8.6
Shader Model
6.8
6.8
Physical
Slot Width
IGP
—
Outputs
Portable Device Dependent
Portable Device Dependent
Bus Interface
PCIe 4.0 x8
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
Polaris Mobile
GeForce 20 Mobile
View Radeon RX 6800S Details View GeForce RTX 3080 Mobile Details