Intel UHD Graphics 710 Mobile vs NVIDIA Jetson Orin Nano Super Comparison

Head-to-Head Benchmarks

The recorded database contains no benchmark entries for either the Intel UHD Graphics 710 Mobile or the NVIDIA Jetson Orin Nano Super. Both products have an average benchmark score of zero, and neither has any nearest rivals listed. Consequently, there are no head-to-head performance deltas, no percentile comparisons against other GPUs, and no wins recorded for either side in the head-to-head table.

What can be stated from the data is the theoretical compute ceiling each part offers, based on the recorded specification fields. The NVIDIA Jetson Orin Nano Super delivers a FP32 throughput of 2.089 TFLOPS, which is substantially higher than the Intel UHD Graphics 710 Mobile at 307.2 GFLOPS. In raw single-precision math, the NVIDIA part is roughly 6.8 times faster, a figure derived directly from the two FP32 values in the database. The FP16 comparison follows the same pattern: the Jetson Orin Nano Super reaches 4.178 TFLOPS FP16, while the Intel solution tops out at 614.4 GFLOPS FP16, a ratio of about 6.8 to 1 as well.

Texture and pixel throughput also favor the NVIDIA chip. The Jetson Orin Nano Super has a texture rate of 32.64 GTexel/s compared to 9.600 GTexel/s for the Intel UHD Graphics 710 Mobile, meaning the NVIDIA part processes textures at roughly 3.4 times the rate. Pixel fill rate shows a similar gap: 16.32 GPixel/s versus 4.800 GPixel/s, a 3.4x advantage. These numbers reflect the underlying hardware counts, with the NVIDIA chip carrying 1024 shading units, 32 texture mapping units, and 16 render output units, against 128 shading units, 8 TMUs, and 4 ROPs for the Intel part.

Because there are no actual workload benchmarks in the database, these figures represent theoretical peaks rather than measured application performance. The database indicates both products sit at the 50th percentile among all GPUs, but with zero average benchmark scores, this percentile value is not informative for comparing the two directly. The only honest conclusion from the head-to-head section is that on paper, the Jetson Orin Nano Super has a commanding lead in every computational metric recorded, but no tested performance data exists to confirm real-world scaling.

Architecture Differences

The two parts come from different foundries and process nodes. Intel builds the UHD Graphics 710 Mobile on a 10 nm process at Intel's own fabs, while NVIDIA produces the Jetson Orin Nano Super on an 8 nm node at Samsung. The Intel chip uses the Raptor Lake HD Graphics-M generation, based on Intel's Generation 12.2 architecture. The NVIDIA part uses the GA10B chip, built on the Ampere architecture, within the Tegra product family.

The Intel solution is an integrated graphics processor with 128 shading units, 8 TMUs, and 4 ROPs. It has no dedicated tensor cores, no ray tracing cores, and no separate memory bus; the memory interface is marked as "System Shared" for size, type, and bus width, with bandwidth listed as "System Dependent." The base clock runs at 300 MHz and the boost at 1200 MHz. The FP32 throughput of 307.2 GFLOPS and FP16 of 614.4 GFLOPS (with a 2:1 ratio) come from these limited execution resources. The bus interface is a Ring Bus, typical for an integrated part.

The NVIDIA Jetson Orin Nano Super is a system-on-module with 1024 shading units, 32 TMUs, 16 ROPs, and 32 tensor cores. It uses 8 GB of LPDDR5 memory on a 128-bit bus, delivering 102.4 GB/s of bandwidth. The memory clock is listed at 800 MHz with 6.4 Gbps effective transfer. The chip has a die size of 200 mm², while the Intel part has no recorded die size. The NVIDIA module connects via PCIe 4.0 x4, a discrete-style interface, even though it is classified as an IGP in the slot width field. The physical dimensions are 70 mm by 45 mm, while the Intel part has no recorded length or height.

The API support differs slightly. The Intel part supports DirectX 12 (12_1), while the NVIDIA chip supports DirectX 12 Ultimate (12_2), a higher feature level. Both support OpenGL 4.6 and Vulkan 1.4. The presence of 32 tensor cores on the NVIDIA part indicates hardware acceleration for tensor operations, which the Intel GPU entirely lacks. Neither part has ray tracing cores, so RT performance is not a differentiator.

The power envelope also differs. The Intel UHD Graphics 710 Mobile has a 15 W TDP, while the NVIDIA Jetson Orin Nano Super is rated at 25 W. Both are classified as IGP in slot width, meaning they are not discrete add-in cards, and both have display outputs marked as "Portable Device Dependent."

The release dates are roughly two years apart. Intel launched the UHD Graphics 710 Mobile on January 3, 2023, while NVIDIA's Jetson Orin Nano Super arrived on December 16, 2024. The Intel part lists a successor in Arc Graphics-M, while the NVIDIA part has no successor recorded. The NVIDIA module has a launch MSRP of 249 USD, whereas the Intel part has no recorded launch MSRP.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The NVIDIA Jetson Orin Nano Super delivers 2.089 TFLOPS FP32, compared to 307.2 GFLOPS for the Intel UHD Graphics 710 Mobile. The NVIDIA part is approximately 6.8 times faster in single-precision throughput.

Q: Does the Intel UHD Graphics 710 Mobile have tensor cores?

A: No. The database lists no tensor cores for the Intel part. The NVIDIA Jetson Orin Nano Super includes 32 tensor cores, which are not present on the Intel GPU.

Q: What memory configuration does each product use?

A: The Intel UHD Graphics 710 Mobile uses system shared memory, with size, type, bus width, and bandwidth all marked as system-dependent. The NVIDIA Jetson Orin Nano Super uses 8 GB of LPDDR5 memory on a 128-bit bus with 102.4 GB/s bandwidth.

Q: Which product supports a higher DirectX version?

A: The NVIDIA Jetson Orin Nano Super supports DirectX 12 Ultimate (12_2), while the Intel UHD Graphics 710 Mobile supports DirectX 12 (12_1). Both products support OpenGL 4.6 and Vulkan 1.4.

Q: What is the process node difference between the two?

A: The Intel UHD Graphics 710 Mobile is fabricated on a 10 nm process at Intel, while the NVIDIA Jetson Orin Nano Super uses an 8 nm process at Samsung. The NVIDIA chip is on a smaller node.

Q: What is the TDP of each product?

A: The Intel UHD Graphics 710 Mobile has a 15 W TDP, while the NVIDIA Jetson Orin Nano Super has a 25 W TDP. The NVIDIA part consumes more power according to the recorded specifications.

Specification Differences

The following fields differ between the Intel UHD Graphics 710 Mobile and the NVIDIA Jetson Orin Nano Super:

• Manufacturer: Intel versus NVIDIA
• Chip: Raptor Lake versus GA10B
• Architecture: Generation 12.2 versus Ampere
• Generation: HD Graphics-M (Raptor Lake) versus Tegra (Ampere)
• Process Node: 10 nm versus 8 nm
• Foundry: Intel versus Samsung
• Die Size: Not recorded versus 200 mm²
• Base Clock: 300 MHz versus not recorded
• Boost Clock: 1200 MHz versus not recorded
• Memory Size: System Shared versus 8 GB
• Memory Type: System Shared versus LPDDR5
• Memory Bus Width: System Shared versus 128 bit
• Memory Bandwidth: System Dependent versus 102.4 GB/s
• Memory Clock: Not recorded versus 800 MHz 6.4 Gbps effective
• Shading Units: 128 versus 1024
• TMUs: 8 versus 32
• ROPs: 4 versus 16
• Tensor Cores: Not recorded versus 32
• Pixel Rate: 4.800 GPixel/s versus 16.32 GPixel/s
• Texture Rate: 9.600 GTexel/s versus 32.64 GTexel/s
• FP32: 307.2 GFLOPS versus 2.089 TFLOPS
• FP16: 614.4 GFLOPS (2:1) versus 4.178 TFLOPS (2:1)
• TDP: 15 W versus 25 W
• Bus Interface: Ring Bus versus PCIe 4.0 x4
• DirectX Support: 12 (12_1) versus 12 Ultimate (12_2)
• Dimensions: No recorded length or height versus 70 mm length, 45 mm height
• Release Date: January 3, 2023 versus December 16, 2024
• Successor: Arc Graphics-M versus not recorded
• Launch MSRP: Not recorded versus 249 USD

Fields that are identical or not recorded on either side include the display outputs (both marked "Portable Device Dependent"), the slot width (both IGP), the power connectors (both null), the suggested PSU (both null), the OpenGL version (both 4.6), the Vulkan version (both 1.4), the production status (both Active), and the absence of ray tracing cores on both.

The Verdict

The data in the database points to a clear performance hierarchy. The NVIDIA Jetson Orin Nano Super holds decisive advantages in every recorded compute metric: roughly 6.8 times the FP32 throughput, 6.8 times the FP16 throughput, 3.4 times the texture rate, and 3.4 times the pixel rate. It also brings 32 tensor cores, a dedicated 8 GB memory pool with 102.4 GB/s of bandwidth, and a smaller 8 nm process node. The Intel UHD Graphics 710 Mobile counters with a lower 15 W TDP, a higher boost clock of 1200 MHz, and an earlier release date, but its system-shared memory and limited execution resources place it firmly in a lower performance tier.

The Jetson Orin Nano Super is the appropriate choice for workloads that need tensor acceleration, higher memory bandwidth, or sustained parallel compute, all of which the recorded specifications support. The Intel part, with its 128 shading units and system-dependent memory, suits basic graphics output in low-power portable devices, where the 15 W envelope and integrated nature are advantages.

The 249 USD launch MSRP for the NVIDIA module, combined with its 25 W TDP and physical dimensions of 70 mm by 45 mm, indicates a compact but more capable compute module. The Intel part has no recorded MSRP and no discrete dimensions, reflecting its role as a built-in GPU rather than a standalone product. Neither part has any recorded benchmark scores, so the verdict rests entirely on the specification sheet, but that sheet is unambiguous about which part delivers more computational capability per the recorded figures.