AMD FirePro W5170M vs NVIDIA GeForce GTX 950M Comparison

The AMD FirePro W5170M and NVIDIA GeForce GTX 950M are two end-of-life mobile graphics solutions from different professional and consumer lineages, respectively. The benchmark data reveals a clear split: the GTX 950M dominates in OpenCL compute workloads, while the FirePro W5170M takes a decisive lead in Vulkan performance. The AMD part edges out the NVIDIA part in overall percentile ranking, but the real story is which API you prioritize, as each GPU leads by a substantial margin in its preferred test.

Where Each One Wins

The NVIDIA GeForce GTX 950M is the clear winner for compute-heavy tasks that leverage OpenCL. Its Geekbench OpenCL score of 9,745 stands 16.5% above the FirePro W5170M’s 8,140, making it the stronger choice for general-purpose GPU compute, data processing, or any workload optimized for NVIDIA’s OpenCL implementation. The GTX 950M also holds a slight edge in raw throughput metrics, with higher pixel rate (17.98 GPixel/s vs 14.80 GPixel/s), texture rate (44.96 GTexel/s vs 37.00 GTexel/s), and FP32 performance (1,438.7 GFLOPS vs 1,184.0 GFLOPS).

The AMD FirePro W5170M wins decisively in Vulkan, scoring 9,050 against the GTX 950M’s 6,525 — a 38.7% advantage. This is a massive gap that indicates the FirePro’s GCN 1.0 architecture and its Vulkan 1.2.170 driver support are far better suited to modern Vulkan-based games and applications. For users running Vulkan titles or Vulkan-compute workloads, the FirePro W5170M delivers performance that the GTX 950M cannot match, despite the latter’s newer release date.

The overall average benchmark scores are close: the FirePro W5170M averages 8,595 (44th percentile of all GPUs), while the GTX 950M averages 8,135 (42nd percentile). The FirePro’s higher percentile ranking reflects its stronger Vulkan showing, which balances out the GTX 950M’s OpenCL advantage. The choice is straightforward: NVIDIA for OpenCL, AMD for Vulkan.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. The AMD FirePro W5170M uses the Tropo chip built on GCN 1.0 architecture, fabricated by TSMC on a 28 nm process. It packs 1,500 million transistors into a 123 mm² die, yielding a transistor density of 12.2M per mm². The NVIDIA GeForce GTX 950M uses the GM107 chip on Maxwell architecture, also fabricated by TSMC on 28 nm, but with a larger 148 mm² die holding 1,870 million transistors (12.6M per mm²). The GTX 950M’s newer Maxwell design gives it higher clock speeds: base 993 MHz and boost 1,124 MHz, compared to the FirePro’s 900 MHz base and 925 MHz boost.

Memory configurations differ significantly. The FirePro W5170M comes with 2 GB of GDDR5 on a 128-bit bus, achieving 72.00 GB/s of bandwidth. The GTX 950M offers 4 GB of DDR3, also on a 128-bit bus, but its bandwidth drops to just 28.80 GB/s — less than half the FirePro’s. Memory type and bandwidth are where the FirePro wins clearly; the GTX 950M compensates with higher capacity. Both GPUs have identical core counts: 640 shading units, 40 TMUs, and 16 ROPs.

API support also differs. The FirePro W5170M supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The GTX 950M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The Vulkan version difference is notable — 1.4 vs 1.2.170 — yet the FirePro still outperforms in Vulkan benchmarks, suggesting driver optimization and architecture are more impactful than API version alone. The GTX 950M has a 75 W TDP, while the FirePro’s TDP is not listed in the data.

Head-to-Head Benchmarks

The two Geekbench tests tell opposite stories. In Geekbench OpenCL, the GTX 950M scores 9,745 versus the FirePro’s 8,140, a delta of -16.5% for the AMD part. This is the NVIDIA card’s strongest showing, and the margin is substantial — nearly one-sixth of the FirePro’s score. The GTX 950M’s higher clock speeds (993 MHz base vs 900 MHz) and larger transistor count (1,870M vs 1,500M) likely drive this advantage, despite the FirePro’s superior memory bandwidth.

In Geekbench Vulkan, the tables turn dramatically. The FirePro W5170M scores 9,050, which is 38.7% higher than the GTX 950M’s 6,525. This is a crushing victory for AMD, and the delta is more than double the OpenCL gap in percentage terms. The FirePro’s Vulkan 1.2.170 driver stack appears far more efficient on GCN 1.0 than NVIDIA’s Maxwell implementation with Vulkan 1.4, even though the NVIDIA card has the newer API version. This suggests that raw API version matters less than how well the hardware and drivers execute the workload.

With one win each, the head-to-head is a perfect split. The average benchmark scores reflect this: the FirePro averages 8,595 (its two scores are 8,140 and 9,050), while the GTX 950M averages 8,135 (9,745 and 6,525). The FirePro’s higher average is due to its Vulkan advantage being larger than the GTX 950M’s OpenCL edge.

FAQ

Q: Which GPU has higher overall average benchmark performance?

A: The AMD FirePro W5170M has an average benchmark score of 8,595, which is higher than the NVIDIA GeForce GTX 950M’s 8,135. The FirePro also sits at the 44th percentile of all GPUs, versus the GTX 950M’s 42nd percentile.

Q: How large is the Vulkan performance gap between the two?

A: The FirePro W5170M scores 9,050 in Geekbench Vulkan, which is 38.7% higher than the GTX 950M’s 6,525. This is the largest single-benchmark advantage between the two cards.

Q: Does the GTX 950M have better memory bandwidth?

A: No. The FirePro W5170M has 72.00 GB/s of bandwidth using GDDR5 memory, while the GTX 950M has only 28.80 GB/s using DDR3. However, the GTX 950M offers 4 GB of memory versus the FirePro’s 2 GB.

Q: Which GPU has higher clock speeds?

A: The NVIDIA GeForce GTX 950M has higher clocks: 993 MHz base and 1,124 MHz boost, compared to the AMD FirePro W5170M’s 900 MHz base and 925 MHz boost.

Q: Are the two GPUs similar in core configuration?

A: Yes, they share identical core counts: both have 640 shading units, 40 TMUs, and 16 ROPs. Their differences come from architecture, clocks, and memory, not raw core counts.

Q: Which GPU is better for OpenCL workloads?

A: The NVIDIA GeForce GTX 950M, which scores 9,745 in Geekbench OpenCL, 16.5% ahead of the FirePro W5170M’s 8,140.

Specification Differences

| Specification | AMD FirePro W5170M | NVIDIA GeForce GTX 950M |

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

| Architecture | GCN 1.0 | Maxwell |

| Transistors | 1,500 million | 1,870 million |

| Die Size | 123 mm² | 148 mm² |

| Transistor Density | 12.2M / mm² | 12.6M / mm² |

| Base Clock | 900 MHz | 993 MHz |

| Boost Clock | 925 MHz | 1,124 MHz |

| Memory Clock | 1,125 MHz (4.5 Gbps effective) | 900 MHz (1,800 Mbps effective) |

| Memory Size | 2 GB | 4 GB |

| Memory Type | GDDR5 | DDR3 |

| Memory Bandwidth | 72.00 GB/s | 28.80 GB/s |

| Pixel Rate | 14.80 GPixel/s | 17.98 GPixel/s |

| Texture Rate | 37.00 GTexel/s | 44.96 GTexel/s |

| FP32 Performance | 1,184.0 GFLOPS | 1,438.7 GFLOPS |

| TDP | Not listed | 75 W |

| Slot Width | MXM Module | IGP |

| Bus Interface | MXM-A (3.0) | PCIe 3.0 x8 |

| DirectX Support | 12 (11_1) | 12 (11_0) |

| Vulkan Support | 1.2.170 | 1.4 |

| Release Date | 2014-08-24 | 2015-03-12 |

| Predecessor | FirePro Mobility | GeForce 800M |

| Successor | Radeon Pro Mobile | GeForce 10 Mobile |

The Verdict

Choose the NVIDIA GeForce GTX 950M if your primary workloads rely on OpenCL. It outperforms the FirePro W5170M by 16.5% in Geekbench OpenCL, and it also leads in pixel rate (17.98 GPixel/s vs 14.80 GPixel/s), texture rate (44.96 GTexel/s vs 37.00 GTexel/s), and FP32 compute (1,438.7 GFLOPS vs 1,184.0 GFLOPS). The GTX 950M’s 4 GB memory capacity doubles the FirePro’s 2 GB, which benefits larger datasets despite its lower bandwidth.

Choose the AMD FirePro W5170M if Vulkan performance is your priority. Its 38.7% lead in Geekbench Vulkan is the single largest margin in any benchmark between these two cards, and it secures a higher overall average score (8,595 vs 8,135) and percentile rank (44th vs 42nd). The FirePro also offers superior memory bandwidth (72.00 GB/s vs 28.80 GB/s) and a higher DirectX feature level (12 (11_1) vs 12 (11_0)).

The data shows a clear trade-off: NVIDIA wins on raw compute throughput and memory capacity, while AMD wins on Vulkan efficiency and memory bandwidth. Neither card is universally faster — the decisive factor is your software stack. If you use OpenCL applications, the GTX 950M is the stronger performer. If you use Vulkan, the FirePro W5170M is the definitive choice. For a balanced average, the FirePro’s higher overall score and percentile make it the marginally better all-rounder, but only because its Vulkan advantage outweighs the GTX 950M’s OpenCL lead.