AMD Radeon Vega 8 Mobile vs NVIDIA GeForce 945M Comparison

Where Each One Wins

The recorded benchmark data splits cleanly between these two mobile graphics solutions. The NVIDIA GeForce 945M takes the single head-to-head OpenCL test, while the AMD Radeon Vega 8 Mobile counters with a Vulkan result that the NVIDIA part cannot match because it has no recorded Vulkan score in the database.

For compute workloads measured through OpenCL, the GeForce 945M is the stronger part. Its score of 8099 beats the Vega 8 Mobile's 7435 by 8.9 percent. That margin is meaningful in the lower midrange of mobile graphics, where small percentage differences often determine playable versus marginal performance. The 945M also sits in the 42nd percentile of all GPUs tracked, three points higher than the Vega 8 Mobile's 39th percentile.

The AMD part wins the feature-completeness argument. It has a recorded Vulkan score of 6970, and its DirectX support reaches 12 (12_1), one tier higher than the NVIDIA chip's DirectX 12 (11_0). For applications that exercise the newer API feature levels, the Vega 8 Mobile has the more current feature set, even if its raw OpenCL number trails.

The use-case split is straightforward. If a workload is OpenCL-based and measured in this database, the GeForce 945M delivers more throughput. If a workload prefers Vulkan or relies on DirectX 12_1 feature levels, the Vega 8 Mobile is the only one of the two with recorded support. The NVIDIA part has no Vulkan entry in the database, so any Vulkan-dependent scenario defaults to the AMD side by default.

Architecture Differences

The two chips represent different design philosophies and fabrication generations. The GeForce 945M uses the GM107 chip built on NVIDIA's Maxwell architecture, manufactured by TSMC on a 28 nm process. The die measures 148 mm² and packs 1,870 million transistors, yielding a transistor density of 12.6 million per square millimeter. Its base clock runs at 928 MHz, boosting to 1020 MHz.

The Vega 8 Mobile uses the Raven-M chip with AMD's GCN 5.0 architecture, built by GlobalFoundries on a 14 nm process. The die is larger at 210 mm² and contains 4,940 million transistors, giving a density of 23.5 million per square millimeter. The clock behavior is unusual: a 300 MHz base clock that boosts to 1101 MHz. That wide boost range reflects how integrated graphics operate, ramping up when thermal and power headroom allow.

Memory handling differs fundamentally. The GeForce 945M has dedicated 2 GB of DDR3 on a 128-bit bus, delivering 28.80 GB/s of bandwidth. The Vega 8 Mobile shares system memory, with its size, type, bus width, and bandwidth all listed as "System Shared" or "System Dependent." This is the classic discrete versus integrated split. The NVIDIA card controls its own memory resources; the AMD IGP depends on the host system's memory configuration.

Compute resources favor the NVIDIA part in raw counts. The 945M has 640 shading units, 40 texture mapping units, and 16 ROPs. The Vega 8 Mobile has 512 shading units, 32 TMUs, and only 8 ROPs. The pixel rate reflects that: 16.32 GPixel/s for NVIDIA versus 8.808 GPixel/s for AMD. Texture rate is closer, 40.80 GTexel/s versus 35.23 GTexel/s. FP32 throughput also favors NVIDIA, 1,305.6 GFLOPS versus 1,127.4 GFLOPS. The AMD part counters with FP16 capability at 2.255 TFLOPS (2:1), a feature the 945M does not list.

Power and form factor diverge as well. The GeForce 945M is an MXM module with a 75 W TDP and no power connectors, using an MXM-B (3.0) bus interface. The Vega 8 Mobile is an IGP with a 25 W TDP, no power connectors, and a system-integrated bus interface. The NVIDIA part is a replaceable module; the AMD part lives on the processor die.

Head-to-Head Benchmarks

The database contains one direct comparison between these two parts: the Geekbench OpenCL test. The GeForce 945M scores 8099, the Vega 8 Mobile scores 7435. That is an 8.9 percent advantage for the NVIDIA chip. To put that in context, the 945M's nearest rivals in the database are the NVIDIA GRID K2 at 8080 (0.2 percent behind), the AMD Radeon R9 M360 at 8129 (0.4 percent ahead), the NVIDIA GeForce GTX 650 Ti Boost at 8067 (0.4 percent behind), and the NVIDIA GeForce GTX 950M at 8135 (0.4 percent ahead). The 945M sits in a tight cluster where a 0.4 percent swing separates it from the next card up or down.

The Vega 8 Mobile's OpenCL score of 7435 places it near the NVIDIA GeForce GTX 750 at 7222 (0.3 percent behind the Vega), the NVIDIA GeForce GTX 560 SE at 7171 (0.4 percent behind), the Intel Iris Pro Graphics P580 at 7170 (0.5 percent behind), and the NVIDIA GeForce GTX 970 at 7157 (0.6 percent behind). Note that the delta percentages here are relative to the Vega 8 Mobile's score, and the GTX 970 appearing this low in the list is a reflection of the specific Geekbench OpenCL workload, not a general statement about that card.

The Vega 8 Mobile also has a Vulkan result of 6970, but the GeForce 945M has no Vulkan score recorded. The head-to-head tally is one win for NVIDIA and zero for AMD, but that tally ignores the Vulkan dimension entirely. The AMD part's average benchmark score across its two recorded tests is 7203, which is lower than its OpenCL score alone because the Vulkan result drags the average down. The NVIDIA part's average is 8099, matching its single OpenCL score.

The 8.9 percent gap in OpenCL is the headline number. It is neither a blowout nor a tie. For a user choosing between a discrete 945M and an integrated Vega 8 Mobile, the OpenCL data says the discrete part delivers roughly nine percent more compute throughput in that specific test.

FAQ

Q: Which GPU has the higher OpenCL score?

A: The NVIDIA GeForce 945M scores 8099 in Geekbench OpenCL, while the AMD Radeon Vega 8 Mobile scores 7435. The NVIDIA part leads by 8.9 percent.

Q: Does the AMD Radeon Vega 8 Mobile support Vulkan?

A: Yes. The database records a Geekbench Vulkan score of 6970 for the Vega 8 Mobile. The NVIDIA GeForce 945M has no Vulkan score recorded in the database.

Q: Which GPU has better DirectX feature level support?

A: The AMD Radeon Vega 8 Mobile supports DirectX 12 (12_1), one tier higher than the NVIDIA GeForce 945M's DirectX 12 (11_0). This means the AMD part can expose newer API features in applications that use them.

Q: How do their memory configurations differ?

A: The GeForce 945M has 2 GB of dedicated DDR3 memory on a 128-bit bus with 28.80 GB/s bandwidth. The Vega 8 Mobile uses system shared memory, with its size, type, bus width, and bandwidth all dependent on the host system.

Q: Which GPU has a higher transistor density?

A: The AMD Radeon Vega 8 Mobile has a transistor density of 23.5 million per square millimeter, built on a 14 nm process. The NVIDIA GeForce 945M has a density of 12.6 million per square millimeter on a 28 nm process.

Q: What is the power draw difference between the two?

A: The GeForce 945M has a 75 W TDP and is an MXM module. The Vega 8 Mobile has a 25 W TDP and is an integrated graphics processor (IGP). The NVIDIA part draws three times the power of the AMD part.

The Verdict

The data supports a clear verdict for different use cases. For pure OpenCL compute throughput, the NVIDIA GeForce 945M is the better choice. Its 8099 score beats the Vega 8 Mobile's 7435 by 8.9 percent, and its 42nd percentile ranking sits above the AMD part's 39th percentile. The 945M also has a dedicated 2 GB memory buffer with 28.80 GB/s of bandwidth, which removes any dependency on system memory performance.

For users who need Vulkan support or DirectX 12_1 feature levels, the AMD Radeon Vega 8 Mobile is the only option with recorded data. It has a Vulkan score of 6970 and a DirectX version of 12 (12_1), while the GeForce 945M has no Vulkan score and only DirectX 12 (11_0). The Vega 8 Mobile also draws 25 W versus 75 W, making it the lower-power solution by a wide margin.

The choice comes down to what the workload requires. If the application uses OpenCL and can tolerate the higher power draw, the GeForce 945M delivers the better measured raw performance. If the application uses Vulkan, needs the newer DirectX feature level, or must run within a 25 W power envelope, the Vega 8 Mobile is the appropriate pick. The database shows one clear OpenCL winner and one clear API-feature winner, with no overlap between those strengths.

Specification Differences

| Specification | NVIDIA GeForce 945M | AMD Radeon Vega 8 Mobile |

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

| Chip | GM107 | Raven-M |

| Architecture | Maxwell | GCN 5.0 |

| Process Node | 28 nm | 14 nm |

| Foundry | TSMC | GlobalFoundries |

| Transistors | 1,870 million | 4,940 million |

| Die Size | 148 mm² | 210 mm² |

| Transistor Density | 12.6M / mm² | 23.5M / mm² |

| Base Clock | 928 MHz | 300 MHz |

| Boost Clock | 1020 MHz | 1101 MHz |

| Memory Size | 2 GB | System Shared |

| Memory Type | DDR3 | System Shared |

| Memory Bus Width | 128 bit | System Shared |

| Memory Bandwidth | 28.80 GB/s | System Dependent |

| Shading Units | 640 | 512 |

| TMUs | 40 | 32 |

| ROPs | 16 | 8 |

| Pixel Rate | 16.32 GPixel/s | 8.808 GPixel/s |

| Texture Rate | 40.80 GTexel/s | 35.23 GTexel/s |

| FP32 | 1,305.6 GFLOPS | 1,127.4 GFLOPS |

| FP16 | Not listed | 2.255 TFLOPS (2:1) |

| TDP | 75 W | 25 W |

| Slot Width | MXM Module | IGP |

| Bus Interface | MXM-B (3.0) | IGP |

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

| Vulkan | 1.4 | 1.3 |

| OpenCL Score | 8099 | 7435 |

| Vulkan Score | Not recorded | 6970 |

| Avg Benchmark Score | 8099 | 7203 |

| Percentile vs All GPUs | 42 | 39 |

| Release Date | 2015-10-26 | 2019-01-07 |

| Production Status | End-of-life | End-of-life |

| Predecessor | GeForce 800M | GCN 3.0 IGP |

| Successor | GeForce 10 Mobile | Navi II IGP |