NVIDIA GeForce 840M vs NVIDIA GeForce GTX 770M Comparison

Head-to-Head Benchmarks

The recorded benchmark data shows a single head-to-head test between the NVIDIA GeForce GTX 770M and the NVIDIA GeForce 840M, and the outcome is decisive. In the Geekbench OpenCL test, the GTX 770M scores 8,552 points, while the 840M records 5,764 points. That translates to a 48.4% advantage for the GTX 770M, a substantial gap that places the two mobile GPUs in clearly different performance tiers.

The OpenCL result is the only direct comparison available in the database, but it aligns with the broader benchmark averages. The GTX 770M carries an average benchmark score of 6,000 across all recorded tests, while the 840M averages 5,322. The difference in average scores is 12.7%, which is smaller than the OpenCL delta but still favors the older, larger chip. The GTX 770M also holds a higher percentile ranking among all GPUs at 35, compared to the 840M at 31. Neither card sits particularly high in the overall distribution, but the GTX 770M consistently outperforms its newer counterpart.

Looking at the closest rivals helps contextualize these scores. The GTX 770M sits within 0.2% of the AMD FirePro W4100 (5,987 average) and the NVIDIA Quadro K4000M (5,986 average), and it is effectively tied with the AMD Radeon RX 6400 at 6,001 and the NVIDIA RTX PRO 6000 Blackwell Server at 5,996. The 840M, by contrast, is nearly identical in average score to the NVIDIA GeForce 930A (5,317, a 0.1% delta) and the NVIDIA GeForce GTX 980M (5,308, a 0.3% delta). It is also within 0.7% of the NVIDIA GeForce 940M (5,284) and trails the AMD Radeon R7 M445 (5,358) by 0.7%. These rival comparisons indicate that the GTX 770M competes in a slightly higher neighborhood of mobile and low-end desktop parts, while the 840M clusters with entry-level Maxwell-based chips.

The single head-to-head win count reflects the OpenCL result: the GTX 770M wins one test, the 840M wins none. There is no Geekbench Metal or Vulkan score recorded for the GTX 770M, and no Metal score for the 840M, so the database only captures the OpenCL comparison. Within that test, the GTX 770M's advantage is not marginal; it is a nearly 50% lead, which points to a fundamental difference in compute throughput rather than a clock-speed optimization or driver quirk.

Architecture Differences

The two GPUs come from different NVIDIA architectures and different generations. The GTX 770M uses the GK106 chip under the Kepler architecture and belongs to the GeForce 700M generation. The 840M uses the GM108S chip under the Maxwell architecture and belongs to the GeForce 800M generation. Both are fabricated by TSMC on the same 28 nm process node, so the architectural differences are not a matter of process scaling.

The transistor counts and die sizes differ significantly. The GTX 770M packs 2,540 million transistors on a 221 mm² die, yielding a transistor density of 11.5 million transistors per square millimeter. The 840M contains 1,020 million transistors on a 77 mm² die, with a higher density of 13.2 million transistors per square millimeter. The Maxwell chip achieves better density despite having far fewer transistors overall, which is consistent with a more streamlined design targeting lower power.

The compute resources tell a clear story. The GTX 770M has 960 shading units, 80 texture mapping units, and 24 ROPs. The 840M has 384 shading units, 16 TMUs, and 8 ROPs. The GTX 770M also produces much higher fill rates: 15.94 GPixel/s pixel rate and 63.76 GTexel/s texture rate, versus 8.992 GPixel/s and 17.98 GTexel/s for the 840M. The FP32 throughput is 1.530 TFLOPS for the GTX 770M, compared to 863.2 GFLOPS for the 840M, a difference of roughly 77% in raw floating-point capability.

Memory architecture is another major divergence. The GTX 770M uses 3 GB of GDDR5 on a 192-bit bus, delivering 96.19 GB/s of bandwidth. The 840M uses 2 GB of DDR3 on a 64-bit bus, delivering only 16.02 GB/s. That bandwidth gap, roughly 6x, is arguably the most consequential difference for real-world performance, especially in memory-bound workloads. The memory clock is listed as 1002 MHz with 4 Gbps effective for the GTX 770M, while the 840M runs at 1001 MHz with 2 Gbps effective.

Power and form factor also separate the two. The GTX 770M carries a 75 W TDP and uses an MXM Module slot width with an MXM-B (3.0) bus interface. The 840M draws only 33 W, fits an IGP slot width, and uses a PCIe 3.0 x8 bus interface. Neither card requires power connectors, and both list display outputs as portable-device dependent. The GTX 770M was released on May 29, 2013, while the 840M followed on March 11, 2014. The GTX 770M's predecessor is the GeForce 600M and its successor is the GeForce 800M; the 840M's predecessor is the GeForce 700M and its successor is the GeForce 900M. Both are now end-of-life products.

API support is mostly similar. Both support DirectX 12 (11_0) and OpenGL 4.6. The Vulkan versions differ: the GTX 770M supports Vulkan 1.2.175, while the 840M supports Vulkan 1.4. Neither has ray tracing cores or tensor cores, and neither lists FP16 performance.

FAQ

Q: Which GPU is faster in the recorded head-to-head benchmark?

A: The NVIDIA GeForce GTX 770M wins the Geekbench OpenCL test with a score of 8,552 versus 5,764 for the NVIDIA GeForce 840M, a 48.4% lead.

Q: How do their average benchmark scores compare?

A: The GTX 770M has an average benchmark score of 6,000, while the 840M averages 5,322. The GTX 770M also ranks at the 35th percentile among all GPUs, compared to the 31st percentile for the 840M.

Q: What are the main memory differences between the two?

A: The GTX 770M has 3 GB of GDDR5 on a 192-bit bus with 96.19 GB/s bandwidth. The 840M has 2 GB of DDR3 on a 64-bit bus with 16.02 GB/s bandwidth.

Q: Which GPU has higher power consumption?

A: The GTX 770M has a 75 W TDP, while the 840M has a 33 W TDP. The 840M is the lower-power part by a significant margin.

Q: Do both GPUs support the same APIs?

A: Both support DirectX 12 (11_0) and OpenGL 4.6. The Vulkan support differs: the GTX 770M supports Vulkan 1.2.175, while the 840M supports Vulkan 1.4.

Q: Which GPU has more shading units and texture units?

A: The GTX 770M has 960 shading units, 80 TMUs, and 24 ROPs. The 840M has 384 shading units, 16 TMUs, and 8 ROPs.

Specification Differences

The two GPUs differ across nearly every major specification category. The GTX 770M uses the GK106 chip with Kepler architecture, while the 840M uses the GM108S chip with Maxwell architecture. The GTX 770M belongs to the GeForce 700M generation and the 840M to the GeForce 800M generation. Both use a 28 nm TSMC process, but the GTX 770M has 2,540 million transistors on a 221 mm² die, while the 840M has 1,020 million transistors on a 77 mm² die. Transistor density is 11.5M per mm² for the GTX 770M and 13.2M per mm² for the 840M.

Clock speeds differ as well. The GTX 770M runs at a 706 MHz base clock and 797 MHz boost, while the 840M runs at 1029 MHz base and 1124 MHz boost. Despite the higher clocks on the 840M, the GTX 770M still wins in throughput due to its larger execution resources. Memory clocks are nearly identical at 1002 MHz versus 1001 MHz, but the effective data rate is 4 Gbps for the GTX 770M and 2 Gbps for the 840M.

Memory capacity, type, bus width, and bandwidth all favor the GTX 770M: 3 GB GDDR5 on a 192-bit bus with 96.19 GB/s, versus 2 GB DDR3 on a 64-bit bus with 16.02 GB/s. The shading unit count is 960 versus 384, TMUs are 80 versus 16, and ROPs are 24 versus 8. Pixel rate is 15.94 GPixel/s versus 8.992 GPixel/s, texture rate is 63.76 GTexel/s versus 17.98 GTexel/s, and FP32 is 1.530 TFLOPS versus 863.2 GFLOPS.

TDP is 75 W for the GTX 770M and 33 W for the 840M. Slot width is MXM Module for the GTX 770M and IGP for the 840M. The bus interface is MXM-B (3.0) for the GTX 770M and PCIe 3.0 x8 for the 840M. Neither requires power connectors. Vulkan support differs: 1.2.175 for the GTX 770M and 1.4 for the 840M. Release dates are May 29, 2013, for the GTX 770M and March 11, 2014, for the 840M. The GTX 770M's predecessor is the GeForce 600M and successor is the GeForce 800M; the 840M's predecessor is the GeForce 700M and successor is the GeForce 900M.

Where Each One Wins

The GTX 770M wins in raw compute performance, memory bandwidth, fill rates, and overall benchmark averages. Its 48.4% OpenCL lead over the 840M is the clearest indicator of its superiority in compute-heavy workloads. The 96.19 GB/s memory bandwidth versus 16.02 GB/s gives it a massive advantage in any task that streams large amounts of data, such as texture-heavy rendering or GPGPU compute. The higher pixel rate of 15.94 GPixel/s and texture rate of 63.76 GTexel/s also make it better suited for traditional 3D rasterization, even if its base and boost clocks are lower than the 840M's. The GTX 770M's 35th percentile ranking among all GPUs, versus the 840M's 31st, confirms its position as the stronger of the two in the database's overall distribution.

The 840M wins in power efficiency and form factor. Its 33 W TDP is less than half the GTX 770M's 75 W, making it far better suited to thin and light laptops where thermal and power budgets are tight. Its IGP slot width and PCIe 3.0 x8 interface also point to a more integrated, lower-footprint design compared to the MXM Module of the GTX 770M. The 840M's higher base and boost clocks (1029 MHz and 1124 MHz versus 706 MHz and 797 MHz) show that Maxwell's design compensates for fewer execution units with higher frequencies, which helps in lightly threaded or latency-sensitive workloads. The 840M also has newer Vulkan support at 1.4 versus 1.2.175, which could matter for compatibility with modern Vulkan applications. Its average score of 5,322 is only 12.7% below the GTX 770M's 6,000 despite having roughly one-third of the shading units, proof of the efficiency of the Maxwell architecture.

The Verdict

The data points to a clear performance hierarchy. The NVIDIA GeForce GTX 770M is the faster GPU in absolute terms, with a 48.4% lead in the only head-to-head OpenCL test, a higher average benchmark score of 6,000 versus 5,322, and a higher percentile ranking at 35 versus 31. Its larger memory bus, higher bandwidth, more shading units, and higher fill rates make it the better choice for users who prioritize compute performance and memory throughput over power consumption. The GTX 770M is also the older of the two, released in May 2013, and it belongs to the Kepler generation, so it lacks the newer Vulkan 1.4 support found on the 840M.

The NVIDIA GeForce 840M is the better choice for power-constrained systems. Its 33 W TDP, IGP form factor, and PCIe 3.0 x8 interface make it more appropriate for compact laptops where the GTX 770M's 75 W MXM Module would be impractical. The 840M is also the newer part, released in March 2014, and it belongs to the Maxwell generation with a higher transistor density of 13.2M per mm². Its higher clocks partially offset its smaller execution resources, and its Vulkan 1.4 support is more current.

For a user choosing between the two strictly on benchmark performance, the GTX 770M is the obvious pick. It wins the only recorded head-to-head test by a wide margin, and its average score places it in a peer group that includes the AMD Radeon RX 6400 and NVIDIA RTX PRO 6000 Blackwell Server, while the 840M sits with the NVIDIA GeForce 930A and GeForce 940M. For a user prioritizing battery life, thermals, and portability, the 840M's 33 W TDP and smaller die make it the more practical option. The database records no price for either card, so the decision rests entirely on performance, power, and form factor. Both are end-of-life products, but they serve different segments: the GTX 770M as a higher-performance mobile part and the 840M as an efficient entry-level solution.