AMD Instinct MI350X vs Intel UHD Graphics 770 Mobile Comparison

AMD Instinct MI350X and Intel UHD Graphics 770 Mobile occupy entirely separate segments of the GPU market, and the recorded data reflects this divide clearly. The MI350X is a 3 nm, 1000 W accelerator module built for compute workloads, while the UHD 770 Mobile is a 10 nm, 15 W integrated graphics processor embedded in Raptor Lake mobile chips. With no shared benchmark scores, no nearest rival entries, and no head-to-head results in the database, the comparison relies on architectural specifications, raw throughput figures, and the distinct roles each product serves.

Head-to-Head Benchmarks

The database contains no recorded benchmark scores for either product. The AMD Instinct MI350X shows an average benchmark score of 0 and a percentile ranking of 50, while the Intel UHD Graphics 770 Mobile likewise posts a 0 average score and a 50th percentile placement. With zero head-to-head results, wins A and B both stand at 0. This absence of data does not indicate equivalence; rather, it reflects the fundamental mismatch in purpose. The MI350X is designed for data center acceleration, and the UHD 770 Mobile is a display and basic rendering solution for laptops. No common workload has been measured across both, so the database offers no direct performance comparison.

What the data does provide are theoretical peak rates that illustrate the scale of difference. The MI350X delivers 72.09 TFLOPS of FP32 compute, while the UHD 770 Mobile manages 819.2 GFLOPS. That ratio, 88 times higher for the AMD part, comes directly from the recorded figures. In FP16, the MI350X again posts 72.09 TFLOPS with a 1:1 ratio, whereas the Intel part reaches 1.638 TFLOPS at a 2:1 ratio. Texture rate follows the same pattern: 2,252.8 GTexel/s for the MI350X versus 25.60 GTexel/s for the UHD 770 Mobile. Pixel rate is where the comparison inverts, because the MI350X reports 0 MPixel/s, having no display outputs or rasterization pipeline, while the UHD 770 Mobile outputs 12.80 GPixel/s. The AMD accelerator does not render pixels at all, so any graphics output workload belongs exclusively to the Intel integrated solution.

Architecture Differences

The two chips come from different foundries and process nodes. AMD uses TSMC at 3 nm for the MI350X, while Intel fabricates the UHD 770 Mobile at 10 nm in-house. The MI350X packs 185,000 million transistors on a 2380 mm² die, yielding a transistor density of 77.7 million per square millimeter. The Intel part lists no transistor count, die size, or density in the database, leaving those fields unspecified. The MI350X is built on CDNA 4.0 architecture, part of the Instinct (MIx) generation, with the chip designated MI350 256CU. The UHD 770 Mobile runs Generation 12.2 architecture on the Raptor Lake chip, classified under HD Graphics-M (Raptor Lake).

Core counts diverge sharply. The MI350X contains 16,384 shading units, 1,024 texture mapping units, and 0 ROPs. The UHD 770 Mobile has 256 shading units, 16 TMUs, and 8 ROPs. Clock speeds also differ: the AMD part runs at a 1000 MHz base and 2200 MHz boost, while the Intel part sits at 300 MHz base and 1600 MHz boost. Memory configurations are entirely different classes. The MI350X uses 288 GB of HBM3e on an 8192-bit bus, delivering 8.19 TB/s bandwidth at 2000 MHz with 8 Gbps effective speed. The UHD 770 Mobile uses system shared memory, with type, bus width, and bandwidth all listed as system dependent. No dedicated VRAM exists for the Intel part.

Power and physical design reinforce the separation. The MI350X has a TDP of 1000 W, requires a 1400 W suggested power supply, uses an OAM module slot, and needs no power connectors because it draws power through the module interface. The UHD 770 Mobile has a 15 W TDP, is an IGP, and lists no power connector or suggested PSU. The AMD part connects via PCIe 5.0 x16, while the Intel part uses a Ring Bus interface. The MI350X measures 102 mm by 165 mm, while the Intel integrated solution has no recorded dimensions. The AMD accelerator has no display outputs, whereas the UHD 770 Mobile supports portable device dependent outputs. API support is equally split: the MI350X reports N/A for DirectX, OpenGL, and Vulkan, while the UHD 770 Mobile supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4.

Where Each One Wins

The MI350X wins decisively in compute throughput. Its 72.09 TFLOPS FP32 figure dwarfs the UHD 770 Mobile's 819.2 GFLOPS. For FP16 workloads, the AMD part again leads with 72.09 TFLOPS versus 1.638 TFLOPS. Texture processing also favors the MI350X, with 2,252.8 GTexel/s compared to 25.60 GTexel/s. Memory bandwidth is another landslide: 8.19 TB/s against a system dependent figure that, while unquantified, cannot approach the HBM3e stack. The 288 GB capacity versus system shared memory means the MI350X can hold far larger datasets locally. For scientific simulation, AI training, or large-scale matrix operations, the data shows the MI350X as the only viable option.

The UHD 770 Mobile wins where the MI350X cannot participate. Its 12.80 GPixel/s pixel rate and 8 ROPs enable actual display output and rasterization, functions the AMD accelerator lacks entirely. The Intel part supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, making it suitable for legacy or lightweight graphics applications, video playback, and desktop compositing. Its 15 W TDP and IGP form factor mean it operates within a laptop's power envelope without additional cooling or power delivery. The MI350X, at 1000 W and an OAM module, cannot even be installed in a standard desktop or mobile chassis. The UHD 770 Mobile also has a production status of Active, while the MI350X lists none, and the Intel part has a successor in Arc Graphics-M, indicating a defined product lifecycle.

Release dates place the Intel part first at 2023-01-03, followed by the AMD part at 2025-06-11. The MI350X descends from Radeon Instinct, while the UHD 770 Mobile has no predecessor listed. Neither product has a launch MSRP in the database.

The Verdict

The data separates these products into non-overlapping categories. The AMD Instinct MI350X is a data center accelerator built for throughput: 16,384 shading units, 288 GB of HBM3e, 8.19 TB/s bandwidth, and 72.09 TFLOPS FP32. It has no display outputs, no graphics APIs, and no pixel rate. Its 1000 W TDP and OAM module form factor target rack-mounted servers with 1400 W power supplies. The Intel UHD Graphics 770 Mobile is an integrated graphics processor for laptops, using 256 shading units, system shared memory, and a 15 W TDP. It provides pixel output, DirectX 12 support, and a full graphics API stack.

For compute workloads like FP32 or FP16 heavy calculations, the MI350X is the clear choice, as the recorded throughput figures are orders of magnitude higher. For any task requiring a visual output, the UHD 770 Mobile is the only option, because the MI350X lacks that capability entirely. The absence of benchmark scores means no real-world application testing exists in the database, but the theoretical peaks alone establish the intended use cases. A buyer needing an accelerator for a server would select the MI350X. A laptop manufacturer needing integrated graphics would select the UHD 770 Mobile. No scenario in the data suggests either product could substitute for the other.

FAQ

Q: Which GPU has higher FP32 performance?

A: The AMD Instinct MI350X delivers 72.09 TFLOPS FP32, while the Intel UHD Graphics 770 Mobile provides 819.2 GFLOPS, making the AMD part 88 times higher in raw FP32 throughput.

Q: Does the AMD Instinct MI350X support display outputs?

A: No. The MI350X lists "No outputs" for display connections, and its API support is N/A for DirectX, OpenGL, and Vulkan. The Intel UHD Graphics 770 Mobile, by contrast, supports portable device dependent outputs.

Q: What memory configurations do these GPUs use?

A: The MI350X uses 288 GB of HBM3e memory on an 8192-bit bus with 8.19 TB/s bandwidth. The UHD 770 Mobile uses system shared memory, with type, bus width, and bandwidth all listed as system dependent.

Q: How do the power requirements differ?

A: The MI350X has a 1000 W TDP and requires a 1400 W suggested power supply, while the UHD 770 Mobile has a 15 W TDP and lists no power supply suggestion.

Q: Which GPU supports modern graphics APIs?

A: The UHD 770 Mobile supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The MI350X reports no API support, listing N/A for all three.

Q: What are the release dates for these products?

A: The Intel UHD Graphics 770 Mobile was released on 2023-01-03, and the AMD Instinct MI350X was released on 2025-06-11.

Specification Differences

| Specification | AMD Instinct MI350X | Intel UHD Graphics 770 Mobile |

|---|---|---|

| Manufacturer | AMD | Intel |

| Chip | MI350 256CU | Raptor Lake |

| Architecture | CDNA 4.0 | Generation 12.2 |

| Generation | Instinct (MIx) | HD Graphics-M (Raptor Lake) |

| Process Node | 3 nm | 10 nm |

| Foundry | TSMC | Intel |

| Transistors | 185,000 million | Not listed |

| Die Size | 2380 mm² | Not listed |

| Transistor Density | 77.7M / mm² | Not listed |

| Base Clock | 1000 MHz | 300 MHz |

| Boost Clock | 2200 MHz | 1600 MHz |

| Memory Size | 288 GB | System Shared |

| Memory Type | HBM3e | System Shared |

| Memory Bus Width | 8192 bit | System Shared |

| Memory Bandwidth | 8.19 TB/s | System Dependent |

| Shading Units | 16384 | 256 |

| TMUs | 1024 | 16 |

| ROPs | 0 | 8 |

| Pixel Rate | 0 MPixel/s | 12.80 GPixel/s |

| Texture Rate | 2,252.8 GTexel/s | 25.60 GTexel/s |

| FP32 Performance | 72.09 TFLOPS | 819.2 GFLOPS |

| FP16 Performance | 72.09 TFLOPS (1:1) | 1.638 TFLOPS (2:1) |

| TDP | 1000 W | 15 W |

| Slot Width | OAM Module | IGP |

| Power Connectors | None | Not listed |

| Suggested PSU | 1400 W | Not listed |

| Bus Interface | PCIe 5.0 x16 | Ring Bus |

| Display Outputs | No outputs | Portable Device Dependent |

| DirectX Support | N/A | 12 (12_1) |

| OpenGL Support | N/A | 4.6 |

| Vulkan Support | N/A | 1.4 |

| Length | 102 mm (4 inches) | Not listed |

| Width | 165 mm (6.5 inches) | Not listed |

| Production Status | Not listed | Active |

| Release Date | 2025-06-11 | 2023-01-03 |

| Predecessor | Radeon Instinct | Not listed |

| Successor | Not listed | Arc Graphics-M |