NVIDIA GeForce 840M vs NVIDIA GeForce GTX 765M Comparison

The NVIDIA GeForce GTX 765M and the NVIDIA GeForce 840M are two end-of-life mobile graphics solutions from different NVIDIA generations, yet they occupy nearly the same performance tier according to aggregate data. The GTX 765M, a Kepler-based part from the GeForce 700M family, and the 840M, a Maxwell-based chip from the GeForce 800M family, present an interesting study in architectural evolution versus raw resource allocation. Benchmark data shows the older GTX 765M holding a commanding lead in every shared test, but the 840M counters with dramatically lower power consumption and a more modern feature set. This analysis explores where each chip wins, what the architectural differences mean in practice, and which GPU the data suggests for specific use cases.

Where Each One Wins

The performance split between these two GPUs is starkly one-sided in raw compute terms. The GTX 765M wins both head-to-head benchmark comparisons, capturing 2 wins out of 2 possible tests, while the 840M records zero wins. The GTX 765M's advantage is substantial, leading by 24.5% in Geekbench OpenCL and by 37.6% in Geekbench Vulkan. This indicates that for any compute-heavy or graphics-intensive workload that leverages these APIs, the GTX 765M is the clear choice despite being the older architecture.

However, the 840M's domain is efficiency and integration. With a TDP of 33 W compared to the GTX 765M's 75 W, the 840M draws less than half the power. This makes it the superior option for thin-and-light laptops where battery life and thermal management take priority over raw frame rates. The 840M is also an IGP (Integrated Graphics Processor) form factor, meaning it is designed to be soldered directly onto the motherboard, whereas the GTX 765M uses a removable MXM Module. For users who prioritize a cooler, quieter, and more power-efficient system over maximum performance, the 840M wins by default, even though it loses every benchmark comparison.

The average benchmark scores tell a similar story: the GTX 765M averages 5,501 across all tests, while the 840M averages 5,322. This places the GTX 765M at the 32nd percentile of all GPUs, just one point above the 840M's 31st percentile. In practical terms, both are entry-level performers by modern standards, but the GTX 765M consistently edges out the 840M in every measurable compute scenario.

Architecture Differences

The two GPUs represent distinct architectural philosophies from NVIDIA. The GTX 765M is built on the Kepler architecture, specifically the GK106 chip, fabricated on a 28 nm process at TSMC. This chip contains 2,540 million transistors on a 221 mm² die, yielding a transistor density of 11.5 million per square millimeter. Kepler was designed for high shader counts and wide memory buses, which explains the GTX 765M's 768 shading units, 64 texture mapping units, and 16 raster output units.

In contrast, the 840M uses the Maxwell architecture with the GM108S chip, also on TSMC's 28 nm process. However, the 840M's chip is far smaller and denser: 1,020 million transistors on just 77 mm², achieving a higher transistor density of 13.2 million per square millimeter. Maxwell focused on efficiency per clock, and the 840M reflects this with just 384 shading units, 16 TMUs, and 8 ROPs. The 840M also runs at significantly higher clocks — 1029 MHz base and 1124 MHz boost versus the GTX 765M's 797 MHz base and 863 MHz boost — but this cannot compensate for having half the shading units and a quarter of the texture units.

The memory architectures diverge sharply. The GTX 765M uses 2 GB of GDDR5 on a 128-bit bus, delivering 64.13 GB/s of bandwidth. The 840M uses 2 GB of DDR3 on a 64-bit bus, which yields only 16.02 GB/s — a quarter of the GTX 765M's bandwidth. This is arguably the single most important architectural difference, as memory bandwidth directly impacts texture fill rates and overall throughput in real-world gaming workloads.

Another notable difference is the API support for Vulkan. The GTX 765M supports Vulkan 1.2.175, while the 840M supports a newer Vulkan 1.4. This means the 840M has access to more recent Vulkan extensions and optimizations, which could partially explain why its Vulkan score, while lower, is relatively closer to its OpenCL score than the GTX 765M's gap.

Head-to-Head Benchmarks

The head-to-head data provides a clear quantitative picture of the GTX 765M's dominance. In Geekbench OpenCL, the GTX 765M scores 7,176 against the 840M's 5,764, a difference of 24.5%. This is a significant margin that reflects the GTX 765M's superior raw compute resources — 768 shading units versus 384, and over 1,325 GFLOPS of FP32 performance versus 863 GFLOPS.

The gap widens further in Geekbench Vulkan, where the GTX 765M scores 6,714 versus the 840M's 4,880, a 37.6% advantage. This larger delta in Vulkan is interesting because the 840M supports a newer version of the Vulkan API (1.4 versus 1.2.175). Despite this software advantage, the GTX 765M's hardware resources overwhelm the 840M. The data suggests that the GTX 765M's higher pixel rate (13.81 GPixel/s versus 8.992 GPixel/s) and texture rate (55.23 GTexel/s versus 17.98 GTexel/s) are the deciding factors, as these directly impact graphics pipeline throughput that Vulkan workloads heavily utilize.

It is notably the GTX 765M also has a Geekbench Metal score of 2,612, while the 840M has no Metal benchmark listed. This absence could indicate that the 840M was not tested under Apple's Metal API, or that the GPU does not support it as effectively. The GTX 765M's average benchmark score of 5,501 places it just 0.1% behind the NVIDIA GeForce MX130 and 0.3% ahead of the AMD Radeon R7 M440. The 840M's average of 5,322 sits 0.1% ahead of the NVIDIA GeForce 930A and 0.7% behind the NVIDIA GeForce 940M.

Specification Differences

The key specification differences between these two GPUs are substantial and directly explain their performance gap:

• Chip and Architecture: GTX 765M uses GK106 (Kepler) with 2,540 million transistors; 840M uses GM108S (Maxwell) with 1,020 million transistors.
• Die Size and Density: GTX 765M has a 221 mm² die with 11.5M transistors/mm²; 840M has a 77 mm² die with 13.2M transistors/mm².
• Base and Boost Clocks: GTX 765M runs at 797 MHz base / 863 MHz boost; 840M runs at 1029 MHz base / 1124 MHz boost.
• Memory Type and Bus Width: GTX 765M uses GDDR5 on a 128-bit bus; 840M uses DDR3 on a 64-bit bus.
• Memory Bandwidth: GTX 765M delivers 64.13 GB/s; 840M delivers 16.02 GB/s.
• Shading Units: GTX 765M has 768; 840M has 384.
• TMUs and ROPs: GTX 765M has 64 TMUs and 16 ROPs; 840M has 16 TMUs and 8 ROPs.
• Pixel and Texture Rates: GTX 765M achieves 13.81 GPixel/s and 55.23 GTexel/s; 840M achieves 8.992 GPixel/s and 17.98 GTexel/s.
• FP32 Performance: GTX 765M delivers 1,325.6 GFLOPS; 840M delivers 863.2 GFLOPS.
• TDP: GTX 765M consumes 75 W; 840M consumes 33 W.
• Slot Width / Bus Interface: GTX 765M uses an MXM Module with MXM-B (3.0) interface; 840M is an IGP with PCIe 3.0 x8.
• Vulkan Version: GTX 765M supports 1.2.175; 840M supports 1.4.

FAQ

Q: Which GPU has higher raw compute performance?

A: The GTX 765M, with 1,325.6 GFLOPS of FP32 performance versus the 840M's 863.2 GFLOPS. It also wins both head-to-head benchmarks, leading by 24.5% in OpenCL and 37.6% in Vulkan.

Q: Does the 840M have any advantage over the GTX 765M?

A: Yes, the 840M consumes only 33 W compared to 75 W for the GTX 765M, making it far more power-efficient. It also supports a newer Vulkan version (1.4 versus 1.2.175) and has a higher transistor density (13.2M/mm² versus 11.5M/mm²).

Q: Why is the GTX 765M faster despite having a lower clock speed?

A: The GTX 765M has double the shading units (768 versus 384), four times the TMUs (64 versus 16), and a 128-bit memory bus with GDDR5, delivering 64.13 GB/s bandwidth versus the 840M's 16.02 GB/s. These resource advantages outweigh the 840M's higher clocks.

Q: Which GPU is better for gaming?

A: Based on the benchmark data, the GTX 765M is better for gaming. Its higher pixel rate (13.81 GPixel/s versus 8.992 GPixel/s) and texture rate (55.23 GTexel/s versus 17.98 GTexel/s) indicate superior graphics throughput, and its 37.6% Vulkan advantage suggests better API-level performance.

Q: Are these GPUs comparable in overall performance?

A: Their average benchmark scores are close — 5,501 for the GTX 765M versus 5,322 for the 840M — placing them within 0.1% to 0.7% of similar rivals. However, in direct head-to-head tests, the GTX 765M is consistently and significantly faster.

Q: Which GPU would be better for a thin laptop?

A: The 840M is the better choice for thin laptops because it is an IGP with a 33 W TDP, whereas the GTX 765M requires a removable MXM module and consumes 75 W. The 840M's lower power draw enables smaller cooling solutions and longer battery life.

The Verdict

The data presents a clear split decision. For users who prioritize raw performance, the NVIDIA GeForce GTX 765M is the unequivocal winner. It dominates every shared benchmark, leading by 24.5% in OpenCL and 37.6% in Vulkan. Its superior memory bandwidth (64.13 GB/s versus 16.02 GB/s), double the shading units, and four times the TMUs translate directly into higher frame rates and faster compute in any workload that utilizes these resources. The 765M's 32nd percentile ranking versus all GPUs, alongside its average score of 5,501, confirms it as the stronger performer of the two.

For users who prioritize efficiency and modern integration, the NVIDIA GeForce 840M is the logical pick. Its 33 W TDP enables passively cooled or ultra-thin designs that the 75 W GTX 765M cannot support. The 840M's Maxwell architecture, despite having fewer resources, achieves a higher transistor density and runs at significantly higher clocks (1029 MHz base versus 797 MHz), demonstrating NVIDIA's shift toward efficiency. Its support for Vulkan 1.4 also provides better forward-looking API compatibility. The 840M's 31st percentile ranking is nearly identical to the 765M's, indicating that in aggregate performance, the two are closer than the head-to-head results suggest.

The verdict is straightforward: gamers and compute users should choose the GTX 765M, while those seeking a power-sipping GPU for everyday tasks in a portable chassis should choose the 840M. The GTX 765M's end-of-life status and MXM form factor make it less suitable for new system builds, but its benchmark dominance is undeniable. The 840M, also end-of-life, offers a glimpse into the efficiency-focused future that Maxwell would bring to later generations, but it cannot overcome the GTX 765M's brute-force advantage in this comparison.