AMD Radeon HD 8950M vs NVIDIA GeForce GTX 1070 Ti Comparison
AMD Radeon HD 8950M
GeForce GTX 1070 Ti
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon HD 8950M vs NVIDIA GeForce GTX 1070 Ti
The NVIDIA GeForce GTX 1070 Ti and AMD Radeon HD 8950M occupy vastly different eras and performance tiers, yet both remain end-of-life products in the benchmark database. The data reveals a decisive mismatch: the GTX 1070 Ti wins both shared head-to-head tests by margins of 257.4% and 370%, making it the clear performance king. However, the HD 8950M’s nearest rivals include the AMD Radeon RX 5500M and Radeon Pro 555, indicating it still holds its own within its own niche of mobile workstation graphics. The following analysis breaks down the benchmark results, architectural gulf, and practical use cases for each card strictly from the fact pack.
Head-to-Head Benchmarks
The two cards share only two benchmark results in the database: Geekbench OpenCL and Geekbench Vulkan. In both, the NVIDIA GeForce GTX 1070 Ti delivers a crushing victory. In Geekbench OpenCL, the GTX 1070 Ti scores 49,219 against the HD 8950M’s 13,772, a delta of 257.4% in NVIDIA’s favor. That is not a marginal win; it is a three-and-a-half-fold performance advantage in raw compute throughput, reflecting the fundamental gap in shading units (2,432 vs 768) and FP32 output (8.186 TFLOPS vs 1.651 TFLOPS).
The Vulkan result is even more lopsided. The GTX 1070 Ti posts 61,006 points, while the HD 8950M manages just 12,979, a 370% delta. This suggests that the Pascal architecture’s Vulkan 1.4 support and higher memory bandwidth (256.3 GB/s vs 88.00 GB/s) translate into far better API-level efficiency. For context, the GTX 1070 Ti’s average benchmark score of 14,277 places it within 0.3% of the Intel Iris Xe MAX Graphics (14,315) and 0.5% below the AMD Radeon Vega 11 (14,352). Meanwhile, the HD 8950M’s average score of 13,376 sits 0.2% above the AMD Radeon RX 5500M (13,356) and 0.2% below the AMD FirePro M6100 (13,354).
The deltas between each card and its nearest rivals are tiny—under 1% in all cases—which means the GTX 1070 Ti and HD 8950M are both tightly clustered with their competitors. Yet the head-to-head delta of 257-370% is an order of magnitude larger. This is not a close contest; it is a generational chasm. The GTX 1070 Ti also holds wins in Passmark DirectX 9 (207), DirectX 11 (107), and G3D (14,674), though the HD 8950M has no comparable Passmark scores to compare directly. The data shows no scenario where the HD 8950M closes the gap.
Where Each One Wins
The GTX 1070 Ti wins every shared benchmark, so its strengths are straightforward: it dominates in compute-heavy workloads like OpenCL and Vulkan, where its 8.186 TFLOPS FP32 and 64 ROPs deliver massive throughput. Its Passmark G3D score of 14,674 and GPU Compute score of 7,165 further confirm its suitability for gaming and general 3D rendering. The card also excels in DirectX 12 scenarios, as evidenced by its 3DMark Steel Nomad DX12 score of 1,471 and Passmark DirectX 12 score of 51, though these are not directly compared to the HD 8950M. With 8 GB of GDDR5 memory on a 256-bit bus, it can handle large textures and high-resolution workloads without bottlenecking.
The HD 8950M, despite losing both head-to-head tests, still has a role. Its average benchmark score of 13,376 puts it within 0.2% of the AMD Radeon RX 5500M, a modern mobile GPU, and within 0.4% of the Radeon Pro 555X. That means for its intended mobile form factor (MXM Module), it remains competitive with much newer parts. Its 2 GB GDDR5 memory and 128-bit bus are modest, but its 768 shading units and GCN 2.0 architecture still deliver 1.651 TFLOPS, which is sufficient for older DirectX 11 titles or light productivity tasks. The card’s Vulkan 1.2.170 support is older than the GTX 1070 Ti’s Vulkan 1.4, but it is not obsolete. In short, the HD 8950M wins by being a capable, low-power (100 W) mobile solution where the GTX 1070 Ti’s 180 W desktop card simply cannot fit.
Architecture Differences
The architectural gap between these two GPUs is stark. The GTX 1070 Ti uses the GP104 chip on TSMC’s 16 nm process, packing 7,200 million transistors into a 314 mm² die. The HD 8950M uses the Saturn chip on TSMC’s 28 nm process, with 2,080 million transistors on a 160 mm² die. That is a transistor density of 22.9M per mm² for NVIDIA versus 13.0M per mm² for AMD, meaning the Pascal chip is not only larger but also far more densely packed.
The core configurations tell the story of performance. The GTX 1070 Ti has 2,432 shading units, 152 TMUs, and 64 ROPs, while the HD 8950M has 768 shading units, 48 TMUs, and just 16 ROPs. Pixel rate is 107.7 GPixel/s for NVIDIA versus 17.20 GPixel/s for AMD, and texture rate is 255.8 GTexel/s versus 51.60 GTexel/s. Memory subsystems differ as well: the GTX 1070 Ti has 8 GB GDDR5 on a 256-bit bus with 256.3 GB/s bandwidth, while the HD 8950M has 2 GB GDDR5 on a 128-bit bus with 88.00 GB/s. Clock speeds are not directly comparable—the GTX 1070 Ti has base and boost clocks of 1607 MHz and 1683 MHz, while the HD 8950M lists no base or boost clock, only a memory clock of 1375 MHz (5.5 Gbps effective).
Feature support also diverges. The GTX 1070 Ti supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, while the HD 8950M supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170. The NVIDIA card includes DisplayPort 1.4a outputs and a dual-slot design with a single 8-pin power connector, whereas the HD 8950M is a portable-device-dependent MXM module. The GTX 1070 Ti’s release date is November 2017, four years after the HD 8950M’s May 2013 launch. The GTX 1070 Ti has a launch MSRP of 399 USD; the HD 8950M has no listed launch MSRP.
FAQ
Q: Which card has a higher average benchmark score?
A: The NVIDIA GeForce GTX 1070 Ti has an average benchmark score of 14,277, while the AMD Radeon HD 8950M has an average of 13,376. The GTX 1070 Ti is 0.3% below the Intel Iris Xe MAX Graphics (14,315) and 0.5% below the AMD Radeon Vega 11 (14,352), while the HD 8950M is 0.2% above the AMD Radeon RX 5500M (13,356).
Q: How much faster is the GTX 1070 Ti in Geekbench Vulkan?
A: The GTX 1070 Ti scores 61,006 in Geekbench Vulkan versus 12,979 for the HD 8950M, a delta of 370%. This is the largest performance gap between the two cards in any shared test.
Q: What is the memory configuration difference?
A: The GTX 1070 Ti has 8 GB of GDDR5 on a 256-bit bus with 256.3 GB/s bandwidth, while the HD 8950M has 2 GB of GDDR5 on a 128-bit bus with 88.00 GB/s bandwidth. The NVIDIA card’s memory clock is 2002 MHz (8 Gbps effective), while the AMD card’s is 1375 MHz (5.5 Gbps effective).
Q: Which card has more shading units?
A: The GTX 1070 Ti has 2,432 shading units, compared to 768 on the HD 8950M. This contributes to the NVIDIA card’s FP32 throughput of 8.186 TFLOPS versus 1.651 TFLOPS for AMD.
Q: Are both cards end-of-life?
A: Yes, both the NVIDIA GeForce GTX 1070 Ti and AMD Radeon HD 8950M have a production status of "End-of-life" in the fact pack. The GTX 1070 Ti was released on November 1, 2017, and the HD 8950M on May 13, 2013.
Q: How do the cards compare in terms of process node and die size?
A: The GTX 1070 Ti uses a 16 nm process with a 314 mm² die and 7,200 million transistors, while the HD 8950M uses a 28 nm process with a 160 mm² die and 2,080 million transistors. The transistor density is 22.9M per mm² for NVIDIA versus 13.0M per mm² for AMD.
The Verdict
The data leaves no ambiguity: the NVIDIA GeForce GTX 1070 Ti is the superior GPU in every measurable shared benchmark. With a 257.4% lead in Geekbench OpenCL and a 370% lead in Geekbench Vulkan, it outperforms the AMD Radeon HD 8950M by a factor of three to four in compute workloads. Its 8 GB GDDR5 memory, 256.3 GB/s bandwidth, and 2,432 shading units make it suitable for modern gaming and 3D rendering at high resolutions, while its 180 W TDP and dual-slot design fit a desktop tower. The GTX 1070 Ti’s percentile rank of 56 against all GPUs also places it in the upper half of the database, whereas the HD 8950M sits at percentile 54—a close overall standing that masks the massive gap in absolute performance.
The HD 8950M, by contrast, is a mobile-only MXM module with a 100 W TDP and 2 GB VRAM. Its average score of 13,376 is competitive with the AMD Radeon RX 5500M and Radeon Pro 555, meaning it is not a slouch for its form factor. However, it cannot match the GTX 1070 Ti in any direct test, and its 1.651 TFLOPS FP32 is a fraction of the NVIDIA card’s 8.186 TFLOPS. For users who need desktop-class performance, the GTX 1070 Ti is the only choice. For those constrained to a laptop or compact MXM system, the HD 8950M remains viable for older titles and light workloads, but it is not a substitute for the Pascal card. The verdict is simple: pick the GTX 1070 Ti for raw power, pick the HD 8950M only if the platform demands it.