NVIDIA GeForce GTX 760M vs NVIDIA GeForce GTX 770M Comparison

Where Each One Wins

The benchmark data splits cleanly between these two mobile Kepler parts. The NVIDIA GeForce GTX 770M takes the single head-to-head victory, while the GTX 760M counters with wins in API coverage and efficiency metrics. For compute-heavy workloads, particularly OpenCL, the GTX 770M is the clear choice. The recorded Geekbench OpenCL score of 8552 for the 770M versus 5604 for the 760M represents a 52.6% advantage, a decisive margin in any mobile graphics context.

The GTX 760M, despite losing the compute race, wins on the power efficiency front. Its 55 W TDP is substantially lower than the 770M's 75 W figure, which matters in thin-and-light laptops where thermal headroom is scarce. The 760M also holds a win in API compatibility coverage: it has recorded Geekbench Vulkan scores, while the 770M has none in the database. For users targeting Vulkan-based titles or workloads, the 760M is the only one of the two with measured results to reference.

Use-case split: the GTX 770M is for sustained compute and OpenCL acceleration, the GTX 760M is for lower-power systems and Vulkan workloads. Both parts share the same generation and architecture, but their positioning diverges on where they direct their resources. The 770M allocates more silicon to shading units, texture units, and memory bandwidth, while the 760M trades those for a smaller power envelope and a more modern bus interface.

Architecture Differences

Both GPUs come from the Kepler architecture, fabricated by TSMC on a 28 nm process. The die is identical in size at 221 mm² with 2,540 million transistors, yielding a transistor density of 11.5M per mm². The chip names differ slightly: the 770M uses GK106, while the 760M uses GK106S. This suggests the 760M is a variant or bin of the same physical design, configured with fewer enabled units.

The core counts diverge significantly. The GTX 770M packs 960 shading units, 80 texture mapping units, and 24 raster operation units. The GTX 760M has 768 shading units, 64 TMUs, and 16 ROPs. That is a 25% reduction in shaders, a 20% cut in TMUs, and a 33% reduction in ROPs. These differences directly explain the pixel and texture rate gaps: the 770M delivers 15.94 GPixel/s and 63.76 GTexel/s, while the 760M manages 11.50 GPixel/s and 46.02 GTexel/s.

Clock speeds also favor the 770M. Its base clock runs at 706 MHz with a boost of 797 MHz, compared to 628 MHz base and 719 MHz boost on the 760M. Memory clocks are identical at 1002 MHz, which translates to 4 Gbps effective on both. The memory subsystem is where the gap widens: the 770M uses a 192-bit bus with 3 GB of GDDR5, yielding 96.19 GB/s of bandwidth. The 760M drops to a 128-bit bus with 2 GB of GDDR5, producing 64.13 GB/s. That is a 50% bandwidth advantage for the 770M.

The bus interface differs as well. The 770M uses MXM-B (3.0), while the 760M uses PCIe 3.0 x16. Both are MXM modules in terms of slot width, and both lack dedicated power connectors. The 760M's PCIe interface may simplify integration in some laptop designs. Neither part has ray tracing or tensor cores, as expected for a 2013-era Kepler product. API support is identical: DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175.

Head-to-Head Benchmarks

The only direct comparison in the database is Geekbench OpenCL, and the result is lopsided. The GTX 770M scores 8552, while the GTX 760M scores 5604. The delta is 52.6%, meaning the 770M outperforms the 760M by more than half its own score. This is not a marginal win; it is a generational gap in compute throughput. The FP32 figures corroborate this: the 770M delivers 1.530 TFLOPS against the 760M's 1,104.4 GFLOPS, a 38.5% raw compute advantage.

Breaking down the OpenCL result, the 770M's higher shading unit count and clock speed contribute directly. With 960 shaders at up to 797 MHz boost, the 770M simply has more arithmetic throughput available. The 760M's 768 shaders at 719 MHz boost cannot compensate. Memory bandwidth also plays a role in OpenCL workloads that stream data: 96.19 GB/s versus 64.13 GB/s is a substantial difference.

The GTX 770M also has a Geekbench Metal score of 3448, which the 760M lacks entirely. This gives the 770M coverage in Apple's Metal API ecosystem, though no direct comparison is possible. The 760M counters with a Geekbench Vulkan score of 4868, an API the 770M has no recorded result for. In practice, both GPUs support the same Vulkan version per the spec sheet, but only the 760M has measured data to validate its performance.

The database ranks the 770M in the 35th percentile of all GPUs, while the 760M sits in the 31st percentile. Average benchmark scores are 6000 for the 770M and 5236 for the 760M. The 770M's nearest rivals include the AMD Radeon RX 6400 (6001, 0% delta), NVIDIA RTX PRO 6000 Blackwell Server (5996, 0.1%), AMD FirePro W4100 (5987, 0.2%), and NVIDIA Quadro K4000M (5986, 0.2%). The 760M's nearest rivals are the NVIDIA Quadro 4000M (5211, 0.5%), GeForce 940M (5284, -0.9%), GeForce GTX 980M (5308, -1.3%), and AMD Radeon R7 M260X (5161, 1.5%).

FAQ

Q: Which GPU is faster in OpenCL compute workloads?

A: The GTX 770M is significantly faster, scoring 8552 versus 5604 in Geekbench OpenCL, a 52.6% advantage.

Q: Do both GPUs support the same graphics APIs?

A: Yes, both support DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. However, the 770M has a measured Geekbench Metal score while the 760M has a measured Geekbench Vulkan score.

Q: What is the memory configuration difference?

A: The GTX 770M has 3 GB of GDDR5 on a 192-bit bus with 96.19 GB/s bandwidth. The GTX 760M has 2 GB of GDDR5 on a 128-bit bus with 64.13 GB/s bandwidth.

Q: Which GPU consumes less power?

A: The GTX 760M has a 55 W TDP, while the GTX 770M runs at 75 W. The 760M is the more power-efficient option.

Q: How do these GPUs compare to their nearest rivals in the database?

A: The 770M is essentially tied with the AMD Radeon RX 6400 and NVIDIA RTX PRO 6000 Blackwell Server (0% and 0.1% deltas). The 760M sits within 1.5% of its nearest rivals, including the NVIDIA GeForce 940M (-0.9%) and GeForce GTX 980M (-1.3%).

Q: What is the core configuration difference?

A: The GTX 770M has 960 shading units, 80 TMUs, and 24 ROPs. The GTX 760M has 768 shading units, 64 TMUs, and 16 ROPs.

Specification Differences

| Specification | NVIDIA GeForce GTX 770M | NVIDIA GeForce GTX 760M |

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

| Chip | GK106 | GK106S |

| Base Clock | 706 MHz | 628 MHz |

| Boost Clock | 797 MHz | 719 MHz |

| Memory Size | 3 GB | 2 GB |

| Memory Bus Width | 192 bit | 128 bit |

| Memory Bandwidth | 96.19 GB/s | 64.13 GB/s |

| Shading Units | 960 | 768 |

| TMUs | 80 | 64 |

| ROPs | 24 | 16 |

| Pixel Rate | 15.94 GPixel/s | 11.50 GPixel/s |

| Texture Rate | 63.76 GTexel/s | 46.02 GTexel/s |

| FP32 Performance | 1.530 TFLOPS | 1,104.4 GFLOPS |

| TDP | 75 W | 55 W |

| Bus Interface | MXM-B (3.0) | PCIe 3.0 x16 |

| Geekbench OpenCL | 8552 | 5604 |

| Geekbench Metal | 3448 | Not recorded |

| Geekbench Vulkan | Not recorded | 4868 |

| Percentile (All GPUs) | 35 | 31 |

| Average Benchmark Score | 6000 | 5236 |

Shared specifications include the 28 nm TSMC process, 2,540 million transistors, 221 mm² die size, 11.5M / mm² transistor density, 1002 MHz memory clock (4 Gbps effective), GDDR5 memory type, MXM Module slot width, no power connectors, portable-device-dependent display outputs, DirectX 12 (11_0), OpenGL 4.6, Vulkan 1.2.175, end-of-life production status, release date of May 29, 2013, GeForce 600M predecessor, and GeForce 800M successor. Both parts lack ray tracing and tensor cores.