Intel UHD Graphics 770 Mobile

How It Compares

The Intel UHD Graphics 770 Mobile sits at the 50th percentile among all GPUs in the database, placing it in a strictly mid-pack position with no direct rivals listed in the nearestRivals data. This means the benchmark database does not currently register a single competitor within a measurable deltaPct range of this integrated graphics solution. The absence of nearestRivals entries is telling: the 770 Mobile occupies a performance tier where no discrete or integrated part lands close enough to warrant comparison. Its 819.2 GFLOPS of FP32 compute and 12.80 GPixel/s pixel rate define a narrow performance envelope, and without rival data, the analysis must rely on absolute scores rather than relative positioning. The 50th percentile indicates that half of all GPUs in the database are faster and half are slower, but the lack of nearby rivals suggests this is a solitary point in the distribution rather than a crowded mid-range segment. Benchmark results indicate a part that is neither a standout nor a laggard—it simply exists in a zone where the nearest comparable hardware has yet to be cataloged or has been excluded from the nearestRivals field. For users, this means there is no direct apples-to-apples comparison available; the 770 Mobile's performance must be judged on its own merits and against the broader percentile ranking.

Ray Tracing and Feature Set

The UHD Graphics 770 Mobile has no dedicated ray tracing cores and no tensor cores listed in the FACT PACK, which is consistent with its integrated graphics positioning. The architecture is Generation 12.2, built on Intel's 10 nm process, and it supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The DirectX 12_1 feature level indicates support for conservative rasterization and rasterizer-ordered views, but without RT cores, any ray-traced workloads would fall back to compute-based shaders running on the 256 shading units. The absence of tensor cores means no dedicated hardware for AI acceleration or DLSS-style upscaling; any machine learning inference would use the general-purpose FP32 and FP16 paths. The FP16 throughput of 1.638 TFLOPS (2:1) is exactly double the FP32 figure, indicating a packed math path, but this is a standard feature of the architecture rather than a specialized tensor operation. Vulkan 1.4 support is current and broad, allowing modern API usage, but the lack of RT and tensor hardware limits the feature set to traditional rasterization and compute workloads. The display outputs are portable device dependent, meaning the physical connectors and supported resolutions vary by laptop implementation—there is no fixed output configuration. The bus interface is Ring Bus, which is typical for integrated graphics sharing the system memory fabric, and the memory is system shared with bandwidth that is system dependent, so the actual data throughput will vary based on the host platform's memory configuration.

Benchmark Performance

The benchmark data is sparse: avgBenchmarkScore is 0, and no individual benchmark entries are listed in the benchmarks array. This means the database contains no measured performance scores for the UHD Graphics 770 Mobile, and the 50th percentile ranking is derived from the part's specification position rather than empirical testing. Without benchmark scores, the analysis cannot cite exact deltas against rivals because nearestRivals is empty and the benchmark array is blank. The pixel rate of 12.80 GPixel/s and texture rate of 25.60 GTexel/s provide theoretical throughput ceilings: at 1080p (1920×1080, roughly 2.07 million pixels), the pixel rate could theoretically fill about 6.2 frames per second at full-screen passes, but real-world rendering includes shading, texturing, and memory bandwidth limits that reduce this dramatically. The FP32 compute of 819.2 GFLOPS equates to roughly 0.82 teraflops, which is in the range of entry-level integrated graphics from the same era. The FP16 figure of 1.638 TFLOPS (2:1) suggests that certain shader workloads could see a boost if coded for half-precision, but the lack of tensor cores means no dedicated AI acceleration. The data shows a part that is constrained by its 15 W TDP and system-shared memory, and the benchmark database has not produced a single score to compare against the theoretical specs. This is a significant gap: the 50th percentile ranking is a placeholder, not a measured result, and users should interpret this with caution.

FAQ

Q: Does the Intel UHD Graphics 770 Mobile support ray tracing?

A: No, the FACT PACK lists no ray tracing cores, and the architecture relies on 256 shading units for all rendering; any ray-traced effects would require compute shader fallbacks.

Q: What is the memory configuration for this GPU?

A: The memory size, type, and bus width are all listed as "System Shared," with bandwidth described as "System Dependent," meaning the GPU uses the host system's RAM and the bandwidth varies by platform.

Q: What API versions are supported?

A: The GPU supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, which covers modern gaming and compute APIs but without dedicated hardware acceleration for ray tracing or tensor operations.

Q: What is the thermal design power (TDP)?

A: The TDP is 15 W, which is typical for integrated graphics in mobile processors, and the slot width is listed as "IGP" (integrated graphics processor).

Q: When was this GPU released?

A: The release date is 2023-01-03, and it uses the Raptor Lake chip on Intel's 10 nm process, with the successor being Arc Graphics-M.

Q: What is the pixel and texture throughput?

A: The pixel rate is 12.80 GPixel/s and the texture rate is 25.60 GTexel/s, based on the 8 ROPs and 16 TMUs respectively, with a base clock of 300 MHz and boost clock of 1600 MHz.

Power and Cooling

The UHD Graphics 770 Mobile has a TDP of 15 W, which is a low-power design intended for integrated use in laptops and portable devices. The slot width is listed as "IGP," confirming it is not a discrete card and does not require a separate power connector—the powerConnectors field is null, and there is no suggested PSU listed. The 15 W TDP means the cooling solution is the laptop's system cooling, not a dedicated GPU cooler; heat dissipation is handled through the shared thermal solution for the CPU and GPU on the same die. The base clock of 300 MHz and boost clock of 1600 MHz indicate that power consumption scales with load, but the 15 W ceiling limits sustained performance under heavy load. Because the memory is system shared, the GPU's power draw does not include separate VRAM power; the system RAM is powered independently. The absence of a suggested PSU is expected for an IGP—there is no external power supply requirement, and the GPU draws power from the motherboard's integrated voltage regulators. The 10 nm process node from Intel contributes to the low power envelope, allowing the 15 W TDP to cover both the shading units and the memory controller. For thermal management, the portable device dependent display outputs mean that the cooling solution varies by laptop model, but the 15 W TDP is well within the range of standard mobile cooling designs.

Who Should Consider It

The UHD Graphics 770 Mobile, with its 819.2 GFLOPS FP32 compute and 12.80 GPixel/s pixel rate, is suited for low-resolution and low-detail gaming or general desktop workloads. The 50th percentile ranking among all GPUs suggests it is not a high-performance part, and the absence of benchmark scores means there is no empirical data to suggest it can handle modern AAA titles at high settings. For 1080p gaming, the pixel rate could theoretically support frame rates in the single digits for full-screen effects, but real-world performance would be lower due to shading and memory bandwidth constraints. At 720p or lower resolutions, the GPU might handle esports titles or older games at reduced settings, but the lack of measured benchmarks prevents a definitive recommendation. The system-shared memory with system-dependent bandwidth adds another variable: the GPU's performance will be heavily influenced by the host system's RAM speed and capacity. Users with light productivity needs—web browsing, office applications, video playback—will find the 256 shading units and 16 TMUs adequate for basic tasks. The 15 W TDP makes it ideal for ultra-portable laptops where battery life and low heat are priorities, but gaming performance will be limited to casual or legacy titles. The absence of tensor cores and RT cores means no AI-assisted features or ray-traced effects, so users seeking those capabilities should look elsewhere. The FP16 2:1 throughput of 1.638 TFLOPS could benefit certain compute workloads, but without benchmark scores, the practical impact is unknown.

Memory Subsystem

The memory subsystem is entirely system shared: size, type, and bus width are all listed as "System Shared," with bandwidth described as "System Dependent." This means the GPU does not have dedicated VRAM; it uses a portion of the host system's RAM, and the effective bandwidth is determined by the platform's memory configuration—typically dual-channel DDR4 or DDR5 in modern laptops. The lack of a dedicated bus width figure means the memory interface is whatever the host CPU provides, usually 128-bit for dual-channel configurations, but this is not specified in the FACT PACK. The system-dependent bandwidth has direct implications for high resolutions: at 4K, the GPU would need to read and write significantly more data per frame, and the shared memory bandwidth could become a bottleneck even before the shading units are saturated. The 12.80 GPixel/s pixel rate, combined with the system-shared memory, suggests that the GPU is best suited for 1080p or lower resolutions where memory bandwidth demands are modest. The 256 shading units and 8 ROPs are the primary processing elements, but their effectiveness is gated by how quickly they can access textures and frame buffers in system memory. The FP32 compute of 819.2 GFLOPS and texture rate of 25.60 GTexel/s are theoretical maximums that will rarely be achieved in practice because the memory subsystem is shared with other system processes. For users, this means that upgrading the laptop's RAM speed or enabling dual-channel mode could improve GPU performance, but the FACT PACK does not provide specific numbers to quantify the impact. The system-shared design eliminates the cost and power of dedicated VRAM, aligning with the 15 W TDP, but it also caps the GPU's ability to handle high-resolution textures or large frame buffers without spilling into slower system memory tiers.