AMD Radeon Vega 8 Mobile vs NVIDIA GeForce GTX 950M Comparison

Head-to-Head Benchmarks

The recorded data shows a split decision between the NVIDIA GeForce GTX 950M and the AMD Radeon Vega 8 Mobile, with each card claiming one benchmark victory. The two Geekbench tests tell sharply different stories about where each GPU excels.

In Geekbench OpenCL, the GTX 950M posts a score of 9745 against the Vega 8 Mobile's 7435. That is a 31.1% advantage for the NVIDIA part, a substantial margin that reflects the discrete GPU's dedicated memory pipeline and higher sustained clock behavior. The GTX 950M's average benchmark score across the database sits at 8135, placing it in the 42nd percentile of all GPUs. Its nearest rivals in the database include the AMD Radeon R9 M360 at 8129 (0.1% behind), the NVIDIA GeForce GTX 980 at 8167 (0.4% ahead), the NVIDIA GeForce 945M at 8099 (0.4% behind), and the NVIDIA GRID K2 at 8080 (0.7% behind). The OpenCL result aligns with this neighborhood: the GTX 950M is competitive with midrange discrete parts from its era, and its 31.1% OpenCL lead over the Vega 8 Mobile is the largest head-to-head delta recorded between the two.

The Vulkan benchmark flips the result. Here the AMD Radeon Vega 8 Mobile scores 6970, edging out the GTX 950M's 6525 by 6.4%. This is a narrower margin than the OpenCL gap, but it is still a clear win for the AMD integrated part. The Vega 8 Mobile's average benchmark score is 7203, placing it in the 39th percentile of all GPUs. Its nearest rivals in the database are the NVIDIA GeForce GTX 750 at 7222 (0.3% ahead), the NVIDIA GeForce GTX 560 SE at 7171 (0.4% behind), the Intel Iris Pro Graphics P580 at 7170 (0.5% behind), and the NVIDIA GeForce GTX 970 at 7157 (0.6% behind). The Vulkan result suggests that the Vega 8 Mobile's newer architecture and driver path handle modern API workloads more efficiently than the older Maxwell part, despite the GTX 950M's overall OpenCL dominance.

The head-to-head tally is 1 win each. The GTX 950M takes the compute-oriented OpenCL test by a wide margin, while the Vega 8 Mobile takes the Vulkan test by a modest but definitive 6.4%. Neither GPU dominates the other across both workloads, so the choice between them depends heavily on which API and workload profile matters more to the user.

The Verdict

The data points to a clear division of roles. The NVIDIA GeForce GTX 950M is the stronger choice for OpenCL-heavy compute workloads, where its 31.1% advantage over the Vega 8 Mobile gives it a decisive edge. Its average benchmark score of 8135 also sits notably above the Vega 8 Mobile's 7203, a gap of roughly 12.9% in overall database standing. The GTX 950M's 42nd percentile placement versus the Vega 8 Mobile's 39th percentile reinforces this: the discrete NVIDIA part is the higher-performing GPU on average.

However, the AMD Radeon Vega 8 Mobile wins the Vulkan test by 6.4%, and that is not a trivial result. Vulkan is increasingly relevant in modern gaming and compute contexts, and the Vega 8 Mobile's newer GCN 5.0 architecture appears to handle it more efficiently than the Maxwell-based GTX 950M. For users whose primary workload runs through Vulkan, the AMD part is the better fit.

Picking between them from the data alone: the GTX 950M suits users who prioritize OpenCL performance and overall average benchmark strength. The Vega 8 Mobile suits users who prioritize Vulkan performance and do not need the GTX 950M's raw compute headroom. The GTX 950M also carries a 75 W TDP against the Vega 8 Mobile's 25 W TDP, so the AMD part is far more power-efficient, though the database does not record relative performance-per-watt figures. The Vega 8 Mobile is an integrated GPU while the GTX 950M is a discrete part, which affects system-level integration, but the benchmark data alone shows a 1-1 split with the bigger single-win margin going to NVIDIA.

FAQ

Q: Which GPU wins more benchmarks in the head-to-head comparison?

A: The head-to-head tally is even at 1 win each. The NVIDIA GeForce GTX 950M wins Geekbench OpenCL with a score of 9745 versus 7435, and the AMD Radeon Vega 8 Mobile wins Geekbench Vulkan with a score of 6970 versus 6525.

Q: How large is the GTX 950M's OpenCL advantage over the Vega 8 Mobile?

A: The GTX 950M leads by 31.1% in Geekbench OpenCL, which is the largest delta recorded in the head-to-head benchmark data between these two GPUs.

Q: By how much does the Vega 8 Mobile win the Vulkan test?

A: The Vega 8 Mobile beats the GTX 950M by 6.4% in Geekbench Vulkan, scoring 6970 against 6525.

Q: How do their average benchmark scores compare?

A: The GTX 950M has an average benchmark score of 8135, while the Vega 8 Mobile averages 7203. The GTX 950M also sits in the 42nd percentile of all GPUs, compared to the Vega 8 Mobile's 39th percentile.

Q: What are the nearest rivals for each GPU in the database?

A: For the GTX 950M, the nearest rivals are the AMD Radeon R9 M360 (8129, 0.1% behind), NVIDIA GeForce GTX 980 (8167, 0.4% ahead), NVIDIA GeForce 945M (8099, 0.4% behind), and NVIDIA GRID K2 (8080, 0.7% behind). For the Vega 8 Mobile, the nearest rivals are the NVIDIA GeForce GTX 750 (7222, 0.3% ahead), NVIDIA GeForce GTX 560 SE (7171, 0.4% behind), Intel Iris Pro Graphics P580 (7170, 0.5% behind), and NVIDIA GeForce GTX 970 (7157, 0.6% behind).

Q: Which GPU has the higher TDP?

A: The NVIDIA GeForce GTX 950M has a TDP of 75 W, while the AMD Radeon Vega 8 Mobile has a TDP of 25 W. The Vega 8 Mobile is the more power-efficient part according to the recorded specifications.

Specification Differences

The two GPUs differ across nearly every core specification field in the database. The NVIDIA GeForce GTX 950M uses a 28 nm process node from TSMC, while the AMD Radeon Vega 8 Mobile uses a 14 nm node from GlobalFoundries. The GTX 950M's chip, the GM107, packs 1,870 million transistors on a 148 mm² die, giving a transistor density of 12.6M per mm². The Vega 8 Mobile's Raven-M chip contains 4,940 million transistors on a 210 mm² die, for a density of 23.5M per mm².

Clock speeds differ substantially. The GTX 950M runs at a 993 MHz base clock with a 1124 MHz boost clock. The Vega 8 Mobile runs at a much lower 300 MHz base clock but boosts to 1101 MHz, nearly matching the NVIDIA part's boost. Memory clocks differ too: the GTX 950M uses 900 MHz memory with 1800 Mbps effective, while the Vega 8 Mobile uses system shared memory with no dedicated clock recorded.

Memory specifications are a major differentiator. The GTX 950M has 4 GB of DDR3 memory on a 128-bit bus, delivering 28.80 GB/s of bandwidth. The Vega 8 Mobile uses system shared memory for both capacity and type, with a system shared bus width and bandwidth listed as system dependent. The GTX 950M has a dedicated memory pipeline; the Vega 8 Mobile relies on the host system's memory configuration.

Core counts also differ. The GTX 950M has 640 shading units, 40 texture mapping units, and 16 ROPs. The Vega 8 Mobile has 512 shading units, 32 TMUs, and 8 ROPs. The GTX 950M carries higher pixel and texture rates: 17.98 GPixel/s and 44.96 GTexel/s, versus the Vega 8 Mobile's 8.808 GPixel/s and 35.23 GTexel/s. FP32 compute is 1,438.7 GFLOPS for the GTX 950M and 1,127.4 GFLOPS for the Vega 8 Mobile. The Vega 8 Mobile additionally lists FP16 performance of 2.255 TFLOPS (2:1), while the GTX 950M has no recorded FP16 figure.

The bus interfaces differ: the GTX 950M uses PCIe 3.0 x8, while the Vega 8 Mobile is an IGP with no external bus interface. Both are IGP form factors with no power connectors and portable device dependent display outputs. The GTX 950M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The Vega 8 Mobile supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3. The GTX 950M's production status is end-of-life with a release date of March 12, 2015; the Vega 8 Mobile is also end-of-life with a release date of January 7, 2019.

Architecture Differences

The architectural gap between these two GPUs is significant. The NVIDIA GeForce GTX 950M is built on the Maxwell architecture, dating from the GeForce 900M generation, with the GM107 chip. The AMD Radeon Vega 8 Mobile uses the GCN 5.0 architecture from the Vega IGP (Raven Ridge-M) generation. Maxwell predates GCN 5.0 by several years, and the architectural differences reflect that generational jump.

The manufacturing process is a key divergence: the GTX 950M uses TSMC's 28 nm node, while the Vega 8 Mobile uses GlobalFoundries' 14 nm node. The smaller process node allows the Vega 8 Mobile to pack more transistors into a larger die (4,940 million on 210 mm² versus 1,870 million on 148 mm²), yielding a much higher transistor density of 23.5M per mm² versus 12.6M per mm² for the GTX 950M.

The Vega 8 Mobile's GCN 5.0 architecture is a compute-oriented design with 512 shading units, which is fewer than the GTX 950M's 640, but it compensates with higher clock efficiency at boost (1101 MHz versus 1124 MHz, nearly identical) and a modern API feature set. The Vega 8 Mobile supports DirectX 12 (12_1), a higher feature level than the GTX 950M's DirectX 12 (11_0). The Vega 8 Mobile also lists FP16 support at 2.255 TFLOPS (2:1), which the GTX 950M does not record. The GTX 950M counters with Vulkan 1.4 support versus the Vega 8 Mobile's Vulkan 1.3.

The memory architecture is fundamentally different. The GTX 950M is a discrete GPU with its own 4 GB DDR3 pool on a 128-bit bus, delivering 28.80 GB/s. The Vega 8 Mobile is an integrated GPU that shares system memory, with bandwidth dependent on the host platform. This architectural difference explains much of the GTX 950M's OpenCL advantage: dedicated memory bandwidth and lower latency for compute workloads. Conversely, the Vega 8 Mobile's newer GCN 5.0 design and higher DirectX feature level help it win the Vulkan test despite the memory handicap.

The transistor budgets also reveal intent. The Vega 8 Mobile's Raven-M chip integrates more than just the GPU, as it is an APU-class die with 4,940 million transistors. The GTX 950M's GM107 is a smaller, focused discrete GPU. The Vega 8 Mobile's 25 W TDP versus the GTX 950M's 75 W TDP reflects the integrated part's efficiency goals, though the database does not record per-watt performance deltas. The GTX 950M's predecessor is the GeForce 800M and its successor is the GeForce 10 Mobile; the Vega 8 Mobile's predecessor is the GCN 3.0 IGP and its successor is the Navi II IGP. Both are end-of-life parts, but they represent different architectural eras: Maxwell's mature discrete design versus GCN 5.0's newer integrated approach.