AMD Radeon HD 7770M vs NVIDIA P106-090 Comparison

The AMD Radeon HD 7770M and the NVIDIA P106-090 are two graphics processors separated by five years of architecture evolution, yet they land in the same performance tier. The HD 7770M is a 2012 mobile chip built for laptops, while the P106-090 is a 2017 desktop card designed for mining with no display outputs. Their average benchmark scores are nearly identical — the Radeon averages 13,536 points against the NVIDIA's 13,470 — placing both at the 54th percentile of all GPUs. This parity makes the choice between them a matter of workload fit rather than raw speed.

Where Each One Wins

The benchmark data reveals a clear split in application strengths. The NVIDIA P106-090 dominates in compute-oriented and API-specific workloads. Its Geekbench OpenCL score of 21,304 points is substantially higher than what the HD 7770M achieves in its only recorded benchmark, Geekbench Metal at 13,536 points. For users running OpenCL-accelerated tasks like physics simulations, video encoding, or scientific computing, the P106-090 is the stronger candidate. It also posts a Geekbench Vulkan score of 18,596, showing strong performance in modern graphics APIs.

The AMD Radeon HD 7770M's advantage lies in its specific ecosystem support. Its Geekbench Metal score of 13,536 indicates it can run Apple's Metal API, which the P106-090 cannot — the NVIDIA card has no display outputs and is not designed for interactive graphics. On macOS systems that support Metal, the HD 7770M is the only viable option between the two. However, the Radeon's single benchmark result limits its demonstrated range; there is no OpenCL or Vulkan data for it, so its performance in those APIs remains unquantified.

The P106-090 also wins on architectural maturity. Its DirectX 12 support is rated at 12_1, while the HD 7770M is limited to 12 (11_1). This means the NVIDIA card can handle more advanced DirectX 12 features, which may translate to better performance in newer titles that leverage those capabilities. The Radeon's Vulkan support is 1.2.170, while the NVIDIA card supports Vulkan 1.4, a newer specification revision. For users prioritizing modern API compatibility, the P106-090 has the edge.

Architecture Differences

The two GPUs come from different manufacturing generations and design philosophies. The AMD Radeon HD 7770M uses the Chelsea chip built on GCN 1.0 architecture, fabricated on a 28 nm process at TSMC. It packs 1,500 million transistors into a 123 mm² die, giving a transistor density of 12.2 million per square millimeter. The NVIDIA P106-090 uses the GP106 chip with Pascal architecture, built on a 16 nm process, also at TSMC. It contains 4,400 million transistors across a 200 mm² die, achieving a density of 22.0 million per square millimeter — nearly double the Radeon's density, reflecting the newer process node.

The memory subsystems differ dramatically. The HD 7770M has 1024 MB of GDDR5 on a 128-bit bus, delivering 64.00 GB/s of bandwidth. The P106-090 offers 3 GB of GDDR5 on a 192-bit bus, providing 192.2 GB/s — three times the bandwidth. This is a significant advantage for the NVIDIA card in memory-intensive workloads like high-resolution textures or large datasets. The P106-090 also runs its memory at 2002 MHz (8 Gbps effective) compared to the Radeon's 1000 MHz (4 Gbps effective).

Compute resources favor the NVIDIA card across the board. The P106-090 has 768 shading units, 48 texture mapping units, and 48 ROPs. The HD 7770M has 512 shading units, 32 TMUs, and 16 ROPs. This translates to a pixel rate of 73.49 GPixel/s and texture rate of 73.49 GTexel/s for the NVIDIA card, versus 10.80 GPixel/s and 21.60 GTexel/s for the AMD. The FP32 compute is 2.352 TFLOPS for the P106-090 versus 691.2 GFLOPS for the Radeon — a 3.4x difference in raw compute throughput.

Power and physical specifications also diverge. The HD 7770M is a 32 W part with PCIe 2.0 x16 interface, while the P106-090 draws 75 W, requires a 1x 6-pin power connector, and uses a PCIe 1.0 x1 interface. The NVIDIA card is dual-slot and 250 mm long, while the AMD chip is portable-device-dependent with no fixed dimensions. The P106-090 has no display outputs; the HD 7770M's outputs are also portable-device-dependent, meaning they vary by laptop implementation.

The Verdict

The data supports a clear recommendation based on use case. For raw compute performance in OpenCL or Vulkan workloads, the NVIDIA P106-090 is the superior choice. Its OpenCL score of 21,304 and Vulkan score of 18,596 demonstrate capabilities far beyond what the HD 7770M's single Metal benchmark suggests. The NVIDIA card also brings 3 GB of VRAM, 192.2 GB/s of bandwidth, and a 12_1 DirectX feature level, making it better suited for compute-heavy tasks and modern graphics APIs.

The AMD Radeon HD 7770M is the pick only in scenarios where Metal API support is essential. Its Geekbench Metal score of 13,536 shows it can handle that workload, and the P106-090's lack of display outputs disqualifies it from any interactive graphics role. The Radeon's 32 W power draw also makes it suitable for thin-and-light laptops, while the P106-090 requires a desktop power supply and physical space for a dual-slot card.

Neither card is a clear winner on average scores — the HD 7770M leads by just 0.5% over the P106-090 in their aggregate benchmarks. But the NVIDIA card's architectural advantages in memory bandwidth, compute units, and API support make it the more capable all-rounder for anyone who can work around its lack of display outputs. The Radeon is a niche solution for Metal-specific environments where its lower power draw and mobile form factor are the deciding factors.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon HD 7770M has an average benchmark score of 13,536, which is 0.5% higher than the NVIDIA P106-090's average of 13,470.

Q: Can the NVIDIA P106-090 be used for gaming with a monitor?

A: No. The P106-090 has no display outputs, meaning it cannot connect to a monitor directly. The HD 7770M's display outputs are portable-device-dependent, which typically means they are routed through a laptop's built-in display.

Q: Which card offers better memory bandwidth?

A: The NVIDIA P106-090 offers 192.2 GB/s of bandwidth with 3 GB of GDDR5 on a 192-bit bus, compared to the HD 7770M's 64.00 GB/s with 1024 MB on a 128-bit bus.

Q: Does the AMD card support Vulkan?

A: Yes, the HD 7770M supports Vulkan 1.2.170 and OpenGL 4.6. The P106-090 supports Vulkan 1.4, which is a newer specification.

Q: What is the power consumption difference?

A: The HD 7770M is rated at 32 W TDP, while the P106-090 is rated at 75 W TDP. The NVIDIA card also requires a 1x 6-pin power connector and a 250 W suggested PSU.

Q: Which card has more shading units?

A: The P106-090 has 768 shading units, compared to the HD 7770M's 512. The NVIDIA card also has 48 TMUs and 48 ROPs versus 32 TMUs and 16 ROPs on the AMD part.

Head-to-Head Benchmarks

The most direct comparison available comes from the average benchmark scores. The HD 7770M scores 13,536 in Geekbench Metal, while the P106-090 has no Metal result. Conversely, the P106-090 scores 21,304 in Geekbench OpenCL and 18,596 in Geekbench Vulkan, benchmarks the HD 7770M has no recorded results for. This means the only true cross-comparison is the average score, where the Radeon leads by 0.5% — a margin of just 66 points out of roughly 13,500.

Looking at nearest rivals provides context. The HD 7770M is 0.1% behind the AMD Radeon RX 9070 XT (13,543), 0.2% ahead of the NVIDIA GeForce GTX 570 (13,515), and 1% ahead of the AMD Radeon Pro 555 (13,407). The P106-090 is 0.3% behind the GTX 570, 0.5% ahead of the Radeon Pro 555, and 0.5% behind the HD 7770M. Both cards sit in a tight cluster where less than 1.5% separates the lowest from the highest score.

The biggest wins are in raw throughput. The P106-090's FP32 compute of 2.352 TFLOPS is more than triple the HD 7770M's 691.2 GFLOPS. Its pixel rate of 73.49 GPixel/s is 6.8 times the Radeon's 10.80 GPixel/s. The texture rate of 73.49 GTexel/s versus 21.60 GTexel/s is a 3.4x advantage. Memory bandwidth is 3x higher at 192.2 GB/s versus 64.00 GB/s. These are not marginal differences — they represent a fundamentally more capable chip in the NVIDIA card.

The HD 7770M's only measurable wins are its 0.5% average score lead and its Metal API support. At 32 W versus 75 W, it also draws less than half the power, which is meaningful for mobile applications. But in every compute metric recorded — pixel rate, texture rate, FP32, memory bandwidth, shading units, TMUs, ROPs — the P106-090 is decisively ahead. The average score parity masks a lopsided architectural comparison where the newer Pascal chip simply outclasses the older GCN design in execution resources. The Radeon's single benchmark result appears to be an outlier relative to its hardware specifications, or the Geekbench Metal test weights factors that favor the older architecture. Either way, the data shows the P106-090 as the more powerful processor on paper and in most measurable workloads.