AMD Radeon Vega 10 Mobile vs NVIDIA GeForce GTX 675M Comparison

AMD
RADEON

AMD Radeon Vega 10 Mobile

CORE STATE Raven-M
VRAM System Shared
CLOCK SPEED 1301 MHz
TDP 10 W
BUS WIDTH System Shared
ARCHITECTURE GCN 5.0
nm
PROCESS 14 nm
LAUNCH DATE 2019
VS
NVIDIA
GEFORCE

GeForce GTX 675M

CORE STATE GF114
VRAM 2 GB
CLOCK SPEED —
TDP 100 W
BUS WIDTH 256 bit
ARCHITECTURE Fermi 2.0
nm
PROCESS 40 nm
LAUNCH DATE 2012

PERFORMANCE BENCHMARKS

geekbench_opencl
6,476
6,946

Analysis: AMD Radeon Vega 10 Mobile vs NVIDIA GeForce GTX 675M

NVIDIA GeForce GTX 675M and AMD Radeon Vega 10 Mobile represent two distinct eras of mobile graphics, separated by nearly seven years of architectural evolution. The data shows a single head-to-head benchmark result, with the older discrete GPU holding a clear edge over the much newer integrated solution, yet the story is far more nuanced when considering power efficiency and feature support.

Head-to-Head Benchmarks

The only direct comparison available is the Geekbench OpenCL test, where the NVIDIA GeForce GTX 675M scores 6946 against the AMD Radeon Vega 10 Mobile’s 6476. This gives the GTX 675M a 7.3% victory, a meaningful but not overwhelming margin. Looking at the percentile rankings, the GTX 675M sits at the 39th percentile of all GPUs, while the Vega 10 Mobile lands at the 37th percentile — both are mid-pack performers by this metric, and the 2-percentile gap mirrors the raw score difference.

The GTX 675M’s nearest rivals bracket its performance tightly: the AMD Radeon R5 M240 is just 0.4% behind with a score of 6975, while the NVIDIA GeForce GTX 680M is 1.1% ahead at 7023. This suggests the GTX 675M occupies a very competitive performance tier where even small clock or memory differences shift rankings. On the other side, the Vega 10 Mobile’s closest competitor is the NVIDIA Quadro M5000M, which is only 0.1% behind at 6481, showing that the AMD IGP is punching in the same weight class as a professional mobile workstation part.

Interestingly, the Vega 10 Mobile is 0.6% behind the NVIDIA GeForce GTX 670M (score 6513), meaning AMD’s integrated solution nearly matches the discrete GTX 670M from the same generation as the GTX 675M. The GTX 675M’s 7.3% lead over the Vega 10 Mobile therefore translates to roughly the same performance gap that separates the GTX 675M from its own better-binned sibling, the GTX 680M. The data implies that while the Vega 10 Mobile is competitive with older mid-range discrete parts, it still cannot topple the higher-tier GTX 675M in raw compute throughput.

Both GPUs are end-of-life products, and their benchmark scores reflect their respective historical contexts. The GTX 675M’s single score of 6946 is also its average, indicating consistent performance across runs. The Vega 10 Mobile’s score of 6476 similarly stands as its average. Neither part shows any variance in the data, suggesting stable, reproducible results.

FAQ

Q: Which GPU is faster in the Geekbench OpenCL benchmark?

A: The NVIDIA GeForce GTX 675M scores 6946, which is 7.3% higher than the AMD Radeon Vega 10 Mobile’s 6476. The GTX 675M wins the only head-to-head test.

Q: How does each GPU compare to its nearest rivals?

A: The GTX 675M is 0.4% behind the AMD Radeon R5 M240, 1.1% behind the NVIDIA GeForce GTX 680M, and 1.7% ahead of the AMD FirePro M5100. The Vega 10 Mobile is 0.1% ahead of the NVIDIA Quadro M5000M, 0.3% ahead of the NVIDIA GeForce GT 555M, and 1.1% behind the NVIDIA RTX PRO 5000 72 GB Blackwell.

Q: What are the architectural differences between the two?

A: The GTX 675M uses NVIDIA’s Fermi 2.0 architecture on a 40 nm TSMC process, while the Vega 10 Mobile uses AMD’s GCN 5.0 architecture on a 14 nm GlobalFoundries process. The GTX 675M is a discrete MXM module, whereas the Vega 10 Mobile is an integrated graphics processor (IGP).

Q: Which GPU has higher memory bandwidth?

A: The GTX 675M has dedicated 2 GB GDDR5 memory on a 256-bit bus, delivering 96.00 GB/s bandwidth. The Vega 10 Mobile uses system shared memory with bandwidth described as “System Dependent,” so no fixed figure is available.

Q: Do both GPUs support the same DirectX version?

A: No. The GTX 675M supports DirectX 12 (11_0), while the Vega 10 Mobile supports DirectX 12 (12_1). The Vega 10 Mobile also supports Vulkan 1.3, whereas the GTX 675M has no Vulkan support listed.

Q: What is the power consumption difference?

A: The GTX 675M has a TDP of 100 W, while the Vega 10 Mobile has a TDP of 10 W. This makes the Vega 10 Mobile ten times more power-efficient in terms of thermal design power.

Architecture Differences

The two GPUs are built on fundamentally different foundations. The GTX 675M utilizes NVIDIA’s Fermi 2.0 architecture, fabricated by TSMC on a 40 nm process. Its chip, GF114, packs 1,950 million transistors into a 332 mm² die, yielding a transistor density of 5.9M per mm². The Vega 10 Mobile, in contrast, employs AMD’s GCN 5.0 architecture on GlobalFoundries’ 14 nm node. Its Raven-M chip contains 4,940 million transistors on a much smaller 210 mm² die, achieving a transistor density of 23.5M per mm² — roughly four times higher than the Fermi part.

The compute configurations differ significantly. The GTX 675M has 384 shading units, 64 texture mapping units (TMUs), and 32 raster operation units (ROPs). The Vega 10 Mobile has 640 shading units, 40 TMUs, and only 8 ROPs. Despite having more shading units, the Vega 10 Mobile’s lower ROP count limits its pixel throughput. The GTX 675M achieves a pixel rate of 9.920 GPixel/s, while the Vega 10 Mobile manages 10.41 GPixel/s — a slight edge for the AMD part despite fewer ROPs, likely due to higher clocks.

Texture and compute rates tell a different story. The Vega 10 Mobile delivers 52.04 GTexel/s versus the GTX 675M’s 39.68 GTexel/s, a 31% advantage. In raw FP32 compute, the Vega 10 Mobile hits 1.665 TFLOPS, nearly 75% higher than the GTX 675M’s 952.3 GFLOPS. The Vega 10 Mobile also supports FP16 at 3.331 TFLOPS (2:1 ratio), a feature entirely absent from the Fermi 2.0 part.

Clock behavior also diverges: the GTX 675M lists no base or boost clock, only a memory clock of 750 MHz (3 Gbps effective). The Vega 10 Mobile has a base clock of 300 MHz and a boost clock of 1301 MHz, showing a wide dynamic range typical of modern IGP parts. Memory architecture is another stark contrast — the GTX 675M uses 2 GB of dedicated GDDR5 on a 256-bit bus, while the Vega 10 Mobile relies entirely on system shared memory with no dedicated VRAM.

API support reflects the generational gap. The GTX 675M supports DirectX 12 (11_0) and OpenGL 4.6, but no Vulkan. The Vega 10 Mobile supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3. This means the AMD part is compatible with a wider range of modern graphics APIs, particularly Vulkan-based titles and applications.

The Verdict

The data presents a clear performance hierarchy: the GTX 675M wins the only benchmark by 7.3%, placing it in a higher percentile (39th vs 37th). However, this victory comes with significant caveats. The GTX 675M consumes 100 W of power as a discrete MXM module, whereas the Vega 10 Mobile is an IGP with a 10 W TDP — a tenfold difference in thermal design power. For any application where power efficiency is paramount, the Vega 10 Mobile is the rational choice despite its lower compute score.

The GTX 675M’s dedicated 2 GB GDDR5 with 96.00 GB/s bandwidth is a substantial advantage over system-shared memory, particularly for memory-intensive workloads that benefit from consistent, dedicated bandwidth. Yet the Vega 10 Mobile counters with higher FP32 throughput (1.665 TFLOPS vs 952.3 GFLOPS) and FP16 support, suggesting better raw compute capability for certain tasks that leverage these features.

From a pure performance standpoint, the GTX 675M is the better GPU — it wins the head-to-head and sits in a higher percentile. But the Vega 10 Mobile’s architectural advantages in transistor density, API support, and power efficiency make it a more modern and versatile part. The choice depends entirely on whether raw benchmark dominance or efficiency and feature support take priority.

Specification Differences

| Specification | NVIDIA GeForce GTX 675M | AMD Radeon Vega 10 Mobile |

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

| Architecture | Fermi 2.0 | GCN 5.0 |

| Process Node | 40 nm | 14 nm |

| Foundry | TSMC | GlobalFoundries |

| Transistors | 1,950 million | 4,940 million |

| Die Size | 332 mm² | 210 mm² |

| Transistor Density | 5.9M / mm² | 23.5M / mm² |

| Base Clock | None listed | 300 MHz |

| Boost Clock | None listed | 1301 MHz |

| Memory Size | 2 GB | System Shared |

| Memory Type | GDDR5 | System Shared |

| Memory Bus Width | 256 bit | System Shared |

| Memory Bandwidth | 96.00 GB/s | System Dependent |

| Shading Units | 384 | 640 |

| TMUs | 64 | 40 |

| ROPs | 32 | 8 |

| Pixel Rate | 9.920 GPixel/s | 10.41 GPixel/s |

| Texture Rate | 39.68 GTexel/s | 52.04 GTexel/s |

| FP32 Performance | 952.3 GFLOPS | 1.665 TFLOPS |

| FP16 Performance | None listed | 3.331 TFLOPS (2:1) |

| TDP | 100 W | 10 W |

| Slot Width | MXM Module | IGP |

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

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

| Vulkan Support | None listed | 1.3 |

| Release Date | 2012-03-21 | 2019-01-07 |

Where Each One Wins

The GTX 675M wins in the only direct benchmark, the Geekbench OpenCL test, with a 7.3% higher score. It also holds advantages in dedicated memory bandwidth (96.00 GB/s vs system-dependent), larger memory bus (256 bit vs shared), and higher ROP count (32 vs 8). For applications that rely heavily on memory bandwidth or traditional rasterization throughput, the GTX 675M’s dedicated GDDR5 and higher ROP count give it a structural edge. Its pixel rate of 9.920 GPixel/s is close to the Vega 10 Mobile’s 10.41 GPixel/s, but the NVIDIA part’s memory subsystem is far more predictable.

The Vega 10 Mobile wins in raw compute throughput, delivering 1.665 TFLOPS FP32 versus the GTX 675M’s 952.3 GFLOPS — a 75% advantage. It also offers higher texture rate (52.04 GTexel/s vs 39.68 GTexel/s) and FP16 support at 3.331 TFLOPS, which the NVIDIA part lacks entirely. Its 10 W TDP makes it dramatically more power-efficient, consuming one-tenth the power of the GTX 675M. The Vega 10 Mobile also supports Vulkan 1.3 and DirectX 12 (12_1), providing broader API compatibility for modern software.

For use-case targeting: the GTX 675M suits scenarios where dedicated VRAM and consistent bandwidth are critical, such as older game titles or GPU compute tasks that fit within 2 GB. The Vega 10 Mobile fits thin-and-light laptops where power draw is the primary constraint, and it excels in workloads that leverage its higher FP32 throughput or FP16 capabilities. The data suggests no single winner across all dimensions — the GTX 675M takes the benchmark crown, but the Vega 10 Mobile claims efficiency and compute supremacy.

DETAILED SPECIFICATIONS

SPECIFICATION
Vega 10 Mobile
GTX 675M
Core Specs
Shading Units
640
384 -40.0%
Shaders
640
384 -40.0%
TMUs
40
64 +60.0%
ROPs
8
32 +300.0%
Compute Units
10
—
SM Count
—
8
Clocks
Base Clock
300 MHz
—
Boost Clock
1301 MHz
—
GPU Clock
—
620 MHz
Shader Clock
—
1240 MHz
Memory Clock
System Shared
750 MHz 3 Gbps effective
Memory
Memory Size
System Shared
2 GB
VRAM (MB)
—
2,048
Memory Type
System Shared
GDDR5
Memory Bus
System Shared
256 bit
Bandwidth
System Dependent
96.00 GB/s
Cache
L1 Cache
—
64 KB (per SM)
L2 Cache
—
512 KB
Performance
Pixel Rate
10.41 GPixel/s
9.920 GPixel/s
Texture Rate
52.04 GTexel/s
39.68 GTexel/s
FP32 (TFLOPS)
1.665 TFLOPS
952.3 GFLOPS
FP64 (TFLOPS)
104.1 GFLOPS (1:16)
79.36 GFLOPS (1:12)
FP16 (TFLOPS)
3.331 TFLOPS (2:1)
—
Power
TDP
10 W
100 W
TDP (W)
10
100 +900.0%
Power Connectors
None
None
Architecture
Architecture
GCN 5.0
Fermi 2.0
GPU Name
Raven-M
GF114
Generation
Vega IGP (Raven Ridge-M)
GeForce 600M
Process Size
14 nm
40 nm
Transistors
4,940 million
1,950 million
Die Size
210 mm²
332 mm²
Foundry
GlobalFoundries
TSMC
Density
23.5M / mm²
5.9M / mm²
API Support
DirectX
12 (12_1)
12 (11_0)
OpenGL
4.6
4.6
Vulkan
1.3
—
OpenCL
2.1
1.1
CUDA
—
2.1
Shader Model
6.7
5.1
Physical
Slot Width
IGP
MXM Module
Outputs
Portable Device Dependent
Portable Device Dependent
Bus Interface
IGP
MXM-B (3.0)
Other
Production
End-of-life
End-of-life
Predecessor
GCN 3.0 IGP
GeForce 500M
Successor
Navi II IGP
GeForce 700M
View Radeon Vega 10 Mobile Details View GeForce GTX 675M Details