AMD Radeon HD 8690M vs NVIDIA GeForce GTX 770M Comparison

The AMD Radeon HD 8690M and NVIDIA GeForce GTX 770M are two mobile GPUs from the same era, yet they are engineered for very different tiers of laptop performance. The data shows a clear hierarchy: the GTX 770M is a larger, more powerful chip with a commanding lead in raw compute, while the HD 8690M is a compact, efficient part designed for lighter duties. This analysis breaks down where each card wins based strictly on the benchmark and specification data.

Where Each One Wins

The NVIDIA GeForce GTX 770M is the definitive winner in the only head-to-head benchmark available. In the Geekbench OpenCL test, the GTX 770M scores 8,552 points against the HD 8690M’s 6,137 points, a decisive 28.2% advantage. This is not a marginal victory; it is a substantial gap that indicates the GTX 770M is in a different performance class for general-purpose compute workloads. For any task leveraging OpenCL acceleration, the NVIDIA part is the clear choice.

The AMD Radeon HD 8690M’s "win" is more subtle and not reflected in the head-to-head score. Its advantage lies in its relative positioning against its peers. Despite scoring lower in absolute terms, the HD 8690M has a 36th percentile ranking among all GPUs, while the GTX 770M sits at the 35th percentile. This is a negligible difference in overall standing. However, looking at the nearest rivals, the HD 8690M is only 0.3% behind the Intel Iris Pro Graphics 6200 and 1% behind both the NVIDIA RTX A400 and GeForce MX230. This suggests the HD 8690M is competitive with a newer generation of entry-level parts. The GTX 770M, by contrast, is practically tied with the AMD Radeon RX 6400 and NVIDIA RTX PRO 6000 Blackwell Server, showing it holds its own in a different, more powerful segment. The GTX 770M wins on raw performance; the HD 8690M wins on being a tightly competitive entry-level option.

Architecture Differences

The two GPUs are built on the same 28 nm process node at TSMC, but their internal designs are wildly different. The AMD Radeon HD 8690M uses the "Sun" chip based on the GCN 1.0 architecture. It is a small die, measuring just 56 mm² and packing 690 million transistors. This gives it a transistor density of 12.3M per mm². The NVIDIA GeForce GTX 770M uses the "GK106" chip based on the Kepler architecture, and it is a much larger part. The die size is 221 mm², containing 2,540 million transistors, with a slightly lower density of 11.5M per mm².

The scale of the NVIDIA chip is the primary source of its performance advantage. The GTX 770M has 960 shading units, 80 texture mapping units (TMUs), and 24 render output units (ROPs). In comparison, the AMD part has just 320 shading units, 20 TMUs, and 8 ROPs. This is a 3x advantage in shading units and a 4x advantage in TMUs, which directly translates to the higher fill rates and compute throughput. The NVIDIA card’s pixel rate is 15.94 GPixel/s and its texture rate is 63.76 GTexel/s, versus the AMD card’s 7.800 GPixel/s and 19.50 GTexel/s.

Memory configuration also differs significantly. The GTX 770M comes with 3 GB of GDDR5 memory on a 192-bit bus, yielding a bandwidth of 96.19 GB/s. The HD 8690M has 2 GB of GDDR5 on a 64-bit bus, resulting in a much narrower 32.00 GB/s of bandwidth. Both have similar effective memory clocks (4 Gbps), but the wider bus on the NVIDIA card is crucial for feeding its many cores. The AMD card runs at a higher clock speed (925 MHz base, 975 MHz boost) compared to the NVIDIA card (706 MHz base, 797 MHz boost), but it cannot overcome the massive hardware deficit. The GTX 770M also supports a slightly newer Vulkan version (1.2.175 vs 1.2.170) but has a lower DirectX support level (12 (11_0) vs 12 (11_1)).

Head-to-Head Benchmarks

There is only one direct benchmark comparison in the data: Geekbench OpenCL. The results are unambiguous. The NVIDIA GeForce GTX 770M scores 8,552, while the AMD Radeon HD 8690M scores 6,137. The delta is -28.2% from the perspective of the AMD card, meaning the GTX 770M is approximately 39% faster than the HD 8690M in this test (8552 / 6137 = 1.394). This is a massive gulf in compute performance.

This single score tells the whole story of their relative capabilities. The GTX 770M’s advantage is in raw throughput, driven by its 3x more shading units and 3x memory bandwidth. The HD 8690M’s higher clocks (975 MHz boost vs 797 MHz boost) are insufficient to close the gap. While the HD 8690M could potentially be more efficient per clock or per transistor, the GTX 770M simply has far more hardware to throw at a problem. For any workload that scales with compute cores and memory bandwidth, the GTX 770M will be the victor. The HD 8690M’s only consolation is that its score is closer to its own nearest rivals, showing it is a competent performer in its own low-power class, but it is not in the same league as the GTX 770M.

The Verdict

Strictly from the data, the choice is straightforward for users who need performance. The NVIDIA GeForce GTX 770M is the superior part. Its 28.2% lead in the OpenCL benchmark, coupled with its 3x larger memory bus and 4x texture fill rate, makes it the clear pick for gaming, 3D rendering, or any GPU-accelerated task. The GTX 770M is positioned among much faster rivals in its nearestRivals list, matching the performance of an AMD Radeon RX 6400 and a professional NVIDIA RTX PRO 6000 Blackwell Server in average score.

The AMD Radeon HD 8690M is for a different audience. Its performance is closer to integrated graphics solutions like the Intel Iris Pro Graphics 6200, being only 0.3% slower. It is a low-power, small-die chip that is likely found in thinner, lighter laptops where battery life and thermals are more important than raw speed. For basic multimedia, light photo editing, or older games, the HD 8690M is sufficient. The data shows it is also a more efficient design in terms of die size, using 56 mm² versus the NVIDIA’s 221 mm², though the TDP for the AMD part is not listed.

If you are choosing between two laptops with these GPUs, the decision hinges on your workload. If you need the fastest possible compute and graphics in a mobile form factor, the GTX 770M is the only choice. If you are on a tighter power budget and do not need high-end performance, the HD 8690M offers a baseline of capability that is competitive with its immediate peers, but you will be giving up a massive amount of performance. There is no scenario in the data where the HD 8690M wins on raw performance; the GTX 770M is the definitive winner.

FAQ

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

A: The NVIDIA GeForce GTX 770M is significantly faster, scoring 8,552 points versus the AMD Radeon HD 8690M’s 6,137 points, a 28.2% difference.

Q: How do these GPUs compare to their closest rivals?

A: The HD 8690M is competitive with modern entry-level parts, being just 1% behind the NVIDIA GeForce MX230 and 0.3% behind the Intel Iris Pro Graphics 6200. The GTX 770M is practically tied with the AMD Radeon RX 6400 (0% delta) and the NVIDIA RTX PRO 6000 Blackwell Server (0.1% delta).

Q: What are the main differences in memory configuration?

A: The GTX 770M has 3 GB of GDDR5 memory on a 192-bit bus with 96.19 GB/s bandwidth. The HD 8690M has 2 GB of GDDR5 on a 64-bit bus with a much lower 32.00 GB/s bandwidth.

Q: Which GPU has more shading units?

A: The NVIDIA GeForce GTX 770M has 960 shading units, while the AMD Radeon HD 8690M has only 320. This is a 3x advantage for the NVIDIA card.

Q: Do both GPUs use the same manufacturing process?

A: Yes, both are built on a 28 nm process node at TSMC, but the GTX 770M uses a much larger die (221 mm²) with more transistors (2,540 million) compared to the HD 8690M’s 56 mm² die with 690 million transistors.

Q: What is the percentile ranking for each GPU?

A: The AMD Radeon HD 8690M has a 36th percentile ranking among all GPUs, while the NVIDIA GeForce GTX 770M has a 35th percentile ranking.

Specification Differences

Below are the key specifications where the two GPUs differ, based solely on the fact pack.

| Specification | AMD Radeon HD 8690M | NVIDIA GeForce GTX 770M |

| :--- | :--- | :--- |

| Chip | Sun | GK106 |

| Architecture | GCN 1.0 | Kepler |

| Generation | Solar System (HD 8600M) | GeForce 700M |

| Transistors | 690 million | 2,540 million |

| Die Size | 56 mm² | 221 mm² |

| Transistor Density | 12.3M / mm² | 11.5M / mm² |

| Base Clock | 925 MHz | 706 MHz |

| Boost Clock | 975 MHz | 797 MHz |

| Memory Size | 2 GB | 3 GB |

| Memory Bus Width | 64 bit | 192 bit |

| Memory Bandwidth | 32.00 GB/s | 96.19 GB/s |

| Shading Units | 320 | 960 |

| TMUs | 20 | 80 |

| ROPs | 8 | 24 |

| Pixel Rate | 7.800 GPixel/s | 15.94 GPixel/s |

| Texture Rate | 19.50 GTexel/s | 63.76 GTexel/s |

| FP32 Performance | 624.0 GFLOPS | 1.530 TFLOPS |

| TDP | Not listed | 75 W |

| Slot Width | Not listed | MXM Module |

| Bus Interface | PCIe 3.0 x8 | MXM-B (3.0) |

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

| Vulkan Support | 1.2.170 | 1.2.175 |

| Release Date | 2013-02-28 | 2013-05-29 |

| Predecessor | London | GeForce 600M |

| Successor | Gem System | GeForce 800M |