AMD Radeon Vega 3 vs NVIDIA GeForce GT 735M Comparison
AMD Radeon Vega 3
GeForce GT 735M
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon Vega 3 vs NVIDIA GeForce GT 735M
Head-to-Head Benchmarks
The database contains a single direct benchmark comparison between the AMD Radeon Vega 3 and the NVIDIA GeForce GT 735M, using the Geekbench OpenCL compute workload. In this test, the AMD Radeon Vega 3 scores 3963 points, while the NVIDIA GeForce GT 735M scores 3616 points. This gives the AMD part a 9.6% advantage, a meaningful margin that places it clearly ahead in raw compute throughput.
The AMD Radeon Vega 3's score of 3963 puts it in a competitive position relative to its nearest rivals in the database. It sits within 0.3% of the NVIDIA GeForce GTX 460M (4282 points), within 0.6% of the AMD FirePro W2100 (4295 points), and trails the NVIDIA GeForce RTX 4070 GDDR6 (4335 points) by 1.5%. Meanwhile, it outperforms the NVIDIA Quadro K3000M (4241 points) by 0.6%. These figures indicate that the Vega 3 is positioned in a tight cluster of mid-range mobile and entry-level desktop GPUs, where small percentage differences separate the contenders.
On the other side, the NVIDIA GeForce GT 735M's score of 3616 places it in a similarly dense field. It is within 0.3% of the NVIDIA GeForce GTX 1050 (3629 points), within 0.6% of both the NVIDIA RTX 5000 Mobile Ada Generation (3596 points) and the NVIDIA GeForce GT 545 (3594 points), and trails the AMD Radeon HD 6770 (3649 points) by 0.9%. The GT 735M's position here shows that it is not dramatically slower than its nearest competitors, but the 9.6% gap to the Vega 3 is the decisive factor in this head-to-head.
The percentile rankings reinforce this picture. The AMD Radeon Vega 3 sits at the 25th percentile among all GPUs in the database, while the NVIDIA GeForce GT 735M sits at the 21st percentile. This means the Vega 3 outperforms a slightly larger share of the overall GPU population, consistent with its higher average benchmark score of 4268 versus 3616 for the GT 735M.
The OpenCL result is the only direct comparison available, but it is a compute-centric workload. For tasks that rely heavily on general-purpose GPU compute, such as OpenCL-accelerated filters or physics simulations, the data indicates a clear advantage for the AMD part. The 9.6% delta is not overwhelming, but it is consistent and reproducible in the recorded measurements.
FAQ
Q: Which GPU wins the direct benchmark comparison in the database?
A: The AMD Radeon Vega 3 wins the only head-to-head test, the Geekbench OpenCL benchmark, with a score of 3963 against the NVIDIA GeForce GT 735M's 3616, a 9.6% margin.
Q: How does the AMD Radeon Vega 3 compare to its nearest rivals in average score?
A: The Vega 3's average benchmark score is 4268. It trails the NVIDIA GeForce GTX 460M by 0.3% and the AMD FirePro W2100 by 0.6%, while leading the NVIDIA Quadro K3000M by 0.6% and falling 1.5% short of the NVIDIA GeForce RTX 4070 GDDR6.
Q: What is the NVIDIA GeForce GT 735M's position among its nearest rivals?
A: The GT 735M's average score is 3616. It is 0.3% behind the NVIDIA GeForce GTX 1050, 0.6% ahead of the NVIDIA RTX 5000 Mobile Ada Generation, 0.6% ahead of the NVIDIA GeForce GT 545, and 0.9% behind the AMD Radeon HD 6770.
Q: Which GPU has the higher percentile ranking among all GPUs?
A: The AMD Radeon Vega 3 ranks at the 25th percentile, while the NVIDIA GeForce GT 735M ranks at the 21st percentile, indicating the Vega 3 outperforms a larger share of all GPUs in the database.
Q: Are there multiple benchmark results for the NVIDIA GeForce GT 735M?
A: The database records only one benchmark result for the GT 735M, the Geekbench OpenCL score of 3616. The AMD Radeon Vega 3 has three recorded results: Geekbench Metal at 4880, Geekbench OpenCL at 3963, and Geekbench Vulkan at 3961.
Q: What is the average benchmark score for each GPU?
A: The AMD Radeon Vega 3 has an average benchmark score of 4268, while the NVIDIA GeForce GT 735M has an average benchmark score of 3616.
Architecture Differences
The two GPUs come from fundamentally different architectural lineages. The AMD Radeon Vega 3 is built on the GCN 5.0 architecture, using the Picasso chip, and is fabricated on a 12 nm process at GlobalFoundries. The NVIDIA GeForce GT 735M, by contrast, uses the Kepler 2.0 architecture with the GK208 chip, manufactured on a 28 nm process at TSMC.
The process node difference is significant. The 12 nm node allows the Vega 3 to pack 4,940 million transistors into a 210 mm² die, yielding a transistor density of 23.5 million transistors per square millimeter. The GT 735M's 28 nm node is less dense, with 1,020 million transistors on an 87 mm² die, resulting in 11.7 million transistors per square millimeter. The Vega 3 thus has roughly double the transistor density of the GT 735M.
Clock speeds also differ notably. The Vega 3 has a base clock of 300 MHz and a boost clock of 1100 MHz. The GT 735M has a base clock of 575 MHz and a boost clock of 628 MHz. While the GT 735M starts at a higher base frequency, the Vega 3's boost clock is nearly double that of the GT 735M's boost clock, which explains part of its compute advantage.
The memory subsystems are structured differently. The Vega 3 uses system-shared memory, with its size, type, bus width, and bandwidth all marked as system-dependent. The GT 735M has a dedicated 2 GB of DDR3 memory on a 64-bit bus, with 14.40 GB/s of bandwidth. The GT 735M's dedicated memory is a structural advantage for traditional graphics workloads, but its narrow 64-bit bus limits bandwidth compared to what a system-shared configuration might provide on a modern platform.
Compute unit counts favor the NVIDIA part in raw numbers. The GT 735M has 384 shading units, 32 texture mapping units, and 8 raster operation units. The Vega 3 has 192 shading units, 12 TMUs, and 4 ROPs. Despite having fewer units, the Vega 3 achieves higher compute throughput in the OpenCL benchmark, suggesting that its higher clock speeds and architectural efficiency compensate for the lower unit count.
The API support also differs. The Vega 3 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3. The GT 735M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The Vega 3 has a more feature-complete DirectX 12 implementation and a newer Vulkan version.
Power consumption is another differentiator. The Vega 3 has a TDP of 15 W, while the GT 735M has a TDP of 33 W. The Vega 3 delivers higher compute performance at less than half the power draw, an efficiency advantage that is directly visible in the data.
The Verdict
Based strictly on the recorded measurements, the AMD Radeon Vega 3 is the stronger performer in compute workloads. Its 9.6% lead in the Geekbench OpenCL test is the only direct comparison in the database, and it is a clear win. The Vega 3 also holds a higher percentile ranking (25th versus 21st) and a higher average benchmark score (4268 versus 3616).
The GT 735M does have structural advantages in its dedicated 2 GB of DDR3 memory and its larger number of shading units (384 versus 192). These features could be relevant for graphics tasks that rely on dedicated memory bandwidth or massive parallelism, but the database does not include a direct graphics benchmark to confirm this. In the compute test that is available, the Vega 3 wins.
Users who prioritize compute performance, efficiency, and modern API support should favor the AMD Radeon Vega 3. Its 15 W TDP versus 33 W for the GT 735M, combined with higher performance, makes it the more sensible choice for sustained workloads. Users who need dedicated graphics memory, such as for legacy applications that do not share system memory well, might consider the GT 735M, but the data does not show a performance advantage for it in compute tasks.
Specification Differences
| Specification | AMD Radeon Vega 3 | NVIDIA GeForce GT 735M |
|----------------|-------------------|------------------------|
| Architecture | GCN 5.0 | Kepler 2.0 |
| Chip | Picasso | GK208 |
| Process Node | 12 nm | 28 nm |
| Foundry | GlobalFoundries | TSMC |
| Transistors | 4,940 million | 1,020 million |
| Die Size | 210 mm² | 87 mm² |
| Transistor Density | 23.5M / mm² | 11.7M / mm² |
| Base Clock | 300 MHz | 575 MHz |
| Boost Clock | 1100 MHz | 628 MHz |
| Memory Size | System Shared | 2 GB |
| Memory Type | System Shared | DDR3 |
| Memory Bus Width | System Shared | 64 bit |
| Memory Bandwidth | System Dependent | 14.40 GB/s |
| Shading Units | 192 | 384 |
| TMUs | 12 | 32 |
| ROPs | 4 | 8 |
| Pixel Rate | 4.400 GPixel/s | 5.024 GPixel/s |
| Texture Rate | 13.20 GTexel/s | 20.10 GTexel/s |
| FP32 Performance | 422.4 GFLOPS | 482.3 GFLOPS |
| FP16 Performance | 844.8 GFLOPS (2:1) | null |
| TDP | 15 W | 33 W |
| Bus Interface | IGP | PCIe 3.0 x8 |
| DirectX | 12 (12_1) | 12 (11_0) |
| OpenGL | 4.6 | 4.6 |
| Vulkan | 1.3 | 1.2.175 |
| Release Date | 2019-11-19 | 2013-03-31 |
Where Each One Wins
The AMD Radeon Vega 3 wins in compute performance, as shown by the 9.6% OpenCL lead. It also wins on efficiency, with a 15 W TDP versus 33 W, and on modern API support with DirectX 12 (12_1) and Vulkan 1.3. Its higher boost clock of 1100 MHz versus 628 MHz suggests it can sustain higher throughput in burst workloads. The Vega 3's higher percentile ranking (25th versus 21st) and higher average score (4268 versus 3616) give it the overall edge in the database's metrics.
The NVIDIA GeForce GT 735M wins on raw unit counts, with 384 shading units, 32 TMUs, and 8 ROPs versus 192, 12, and 4 for the Vega 3. It also has a dedicated 2 GB of DDR3 memory with a fixed 14.40 GB/s bandwidth, which is a structural advantage for applications that require dedicated VRAM. Its pixel rate of 5.024 GPixel/s and texture rate of 20.10 GTexel/s are higher than the Vega 3's 4.400 GPixel/s and 13.20 GTexel/s, indicating that for rasterization-heavy tasks, the GT 735M could hold an edge. The GT 735M also has a higher FP32 throughput at 482.3 GFLOPS versus 422.4 GFLOPS for the Vega 3, though this does not translate into a win in the OpenCL benchmark.
For users choosing between these two, the deciding factor is the workload. Compute-heavy applications favor the Vega 3. Graphics-heavy applications with dedicated memory requirements might favor the GT 735M, but the database does not provide direct evidence for that outcome. The only recorded benchmark, Geekbench OpenCL, goes to the AMD part.