Intel Arc G3 vs Intel Arc Pro A60M Comparison

Head-to-Head Benchmarks

The database does not include any head-to-head benchmark entries for the Intel Arc G3 versus the Intel Arc Pro A60M. Both GPUs have an empty benchmark array, an average benchmark score of zero, and zero recorded wins in the comparison table. This means no direct performance measurements exist yet for this pairing. The absence of scores is not an indication of parity; it simply reflects that the G3 is a newly launched part (release date of May 31, 2026) while the Pro A60M has been in the database since June 5, 2023, yet no cross-testing has been logged.

What can be inferred from the recorded data is the theoretical peak throughput. The Arc G3 delivers 6.144 TFLOPS of FP32 compute, which is 0.819 TFLOPS higher than the Pro A60M's 5.325 TFLOPS. That puts the G3 roughly 15.4% ahead in raw shader math based on the FP32 figures. In FP16, the G3 reaches 12.29 TFLOPS (2:1) versus 10.65 TFLOPS (2:1) for the Pro A60M, a gap of 1.64 TFLOPS or about 15.4% again. However, the Pro A60M counters in fill-rate metrics: its pixel rate of 83.20 GPixel/s is 73.3% higher than the G3's 48.00 GPixel/s, and its texture rate of 166.4 GTexel/s is 73.3% higher than the G3's 96.00 GTexel/s. These are not benchmark scores but computed rates from the clock and unit counts, so they serve as a projection of where each part might excel if tested.

Neither GPU has any nearest rivals listed, and both sit at the 50th percentile among all GPUs in the database. That percentile is a placeholder derived from the lack of benchmark data, not a measured ranking. Until actual workloads are recorded, the only quantitative comparison available is the specification-derived throughput and fill rates.

FAQ

Q: Which GPU has a higher FP32 compute throughput?

A: The Intel Arc G3. Its FP32 rating is 6.144 TFLOPS, which is 0.819 TFLOPS higher than the Intel Arc Pro A60M's 5.325 TFLOPS.

Q: What is the memory configuration difference?

A: The Arc Pro A60M has 8 GB of GDDR6 memory on a 128-bit bus with 256.0 GB/s bandwidth. The Arc G3 uses system-shared memory, meaning its memory size, type, bus width, and bandwidth are all system dependent.

Q: Do both GPUs support the same graphics APIs?

A: Yes. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: Which GPU has a higher pixel fill rate?

A: The Arc Pro A60M. Its pixel rate is 83.20 GPixel/s, compared to 48.00 GPixel/s for the Arc G3.

Q: What are the power consumption figures?

A: The Arc G3 has a TDP of 25 W, while the Arc Pro A60M has a TDP of 95 W.

Q: Are there any recorded benchmark scores for either GPU?

A: No. Both GPUs have empty benchmark arrays and an average benchmark score of zero in the database.

The Verdict

Based strictly on the recorded data, the Intel Arc Pro A60M is the stronger choice for rasterization-heavy workloads that depend on fill rate. Its pixel rate of 83.20 GPixel/s and texture rate of 166.4 GTexel/s are substantially above the Arc G3's 48.00 GPixel/s and 96.00 GTexel/s. The Pro A60M also brings dedicated 8 GB GDDR6 memory with 256.0 GB/s bandwidth, which is a fixed resource rather than a system-shared allocation that varies with the host platform. For any task that stresses memory bandwidth, such as high-resolution texturing or compute kernels that repeatedly access large buffers, the Pro A60M's dedicated memory is a clear advantage.

The Intel Arc G3, on the other hand, holds the lead in raw shader compute. Its 6.144 TFLOPS FP32 and 12.29 TFLOPS FP16 surpass the Pro A60M's 5.325 TFLOPS and 10.65 TFLOPS. The G3 also operates at a much lower TDP of 25 W versus 95 W, which makes it suitable for power-constrained platforms. Its boost clock of 2400 MHz is nearly double the Pro A60M's 1300 MHz, and its base clock of 300 MHz is lower, indicating a wider dynamic range. For users who prioritize compute density per watt, the G3 is the data-driven choice.

Neither GPU has any benchmark wins or measured scores, so the verdict rests on specification-derived metrics. The Pro A60M wins on fill rate and memory, the G3 wins on compute throughput and power efficiency. Without actual benchmark results, the choice depends on which workload profile matters more: memory-bound rendering or shader-bound compute.

Specification Differences

| Field | Intel Arc G3 | Intel Arc Pro A60M |

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

| Chip | Panther Lake | DG2-256 |

| Generation | Arc Graphics-M (Panther Lake) | Alchemist (Pro-Series Mobile) |

| Process Node | 3 nm | 6 nm |

| Foundry | Intel | TSMC |

| Transistors | Unknown | 11,500 million |

| Die Size | Unknown | 269 mm² |

| Transistor Density | Not listed | 42.8M / mm² |

| Base Clock | 300 MHz | 900 MHz |

| Boost Clock | 2400 MHz | 1300 MHz |

| Memory Size | System Shared | 8 GB |

| Memory Type | System Shared | GDDR6 |

| Memory Bus Width | System Shared | 128 bit |

| Memory Bandwidth | System Dependent | 256.0 GB/s |

| Memory Clock | System Shared | 2000 MHz, 16 Gbps effective |

| Shading Units | 1280 | 2048 |

| TMUs | 40 | 128 |

| ROPs | 20 | 64 |

| RT Cores | 10 | 16 |

| Pixel Rate | 48.00 GPixel/s | 83.20 GPixel/s |

| Texture Rate | 96.00 GTexel/s | 166.4 GTexel/s |

| FP32 | 6.144 TFLOPS | 5.325 TFLOPS |

| FP16 | 12.29 TFLOPS (2:1) | 10.65 TFLOPS (2:1) |

| TDP | 25 W | 95 W |

| Bus Interface | IGP | PCIe 4.0 x16 |

| Release Date | 2026-05-31 | 2023-06-05 |

Architecture Differences

The two GPUs come from different architecture families. The Intel Arc G3 uses the Xe3-LPG architecture on a 3 nm process fabricated by Intel, and its chip is Panther Lake. The Intel Arc Pro A60M uses the Xe-HPG architecture on a 6 nm process fabricated by TSMC, and its chip is DG2-256. The G3 belongs to the Arc Graphics-M (Panther Lake) generation, while the Pro A60M belongs to the Alchemist (Pro-Series Mobile) generation.

The transistor counts differ substantially: the Pro A60M has 11,500 million transistors on a 269 mm² die with a density of 42.8M per mm², while the G3's transistor count and die size are listed as unknown. The G3's 3 nm node is smaller than the Pro A60M's 6 nm node, which typically allows for higher density and lower power per transistor, but no density figure is provided for the G3 to confirm that.

Core organization differs as well. The Pro A60M has 2048 shading units, 128 TMUs, 64 ROPs, and 16 RT cores. The G3 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores. Despite having 37.5% fewer shading units (1280 versus 2048), the G3 achieves higher FP32 throughput because its boost clock of 2400 MHz is much higher than the Pro A60M's 1300 MHz. The G3 also has a lower base clock of 300 MHz, suggesting a power-management strategy that allows very low idle states but aggressive boosting when needed. The Pro A60M's base clock of 900 MHz is higher, but its boost ceiling is lower.

Memory architecture is a fundamental split. The G3 uses system-shared memory with no dedicated VRAM, making its bandwidth dependent on the host platform's memory subsystem. The Pro A60M has dedicated 8 GB GDDR6 on a 128-bit bus with 256.0 GB/s bandwidth and a 2000 MHz clock operating at 16 Gbps effective. The bus interface also differs: the G3 is an integrated graphics processor (IGP) with no external bus, while the Pro A60M uses PCIe 4.0 x16.

Power delivery reflects these differences: the G3 has a 25 W TDP and no power connectors, while the Pro A60M has a 95 W TDP. Both are listed as IGP slot width, and both have display outputs described as portable device dependent.

Where Each One Wins

The Intel Arc Pro A60M wins in every fill-rate and memory-related metric. Its pixel rate of 83.20 GPixel/s is 73.3% higher than the G3's 48.00 GPixel/s, and its texture rate of 166.4 GTexel/s is 73.3% higher than the G3's 96.00 GTexel/s. This suggests an advantage in rasterization-heavy scenes, high-resolution output, and texture-heavy workloads where the ROP and TMU counts (64 and 128 versus 20 and 40) can be fully utilized. The dedicated 8 GB GDDR6 with 256.0 GB/s bandwidth also removes any dependence on system memory performance, which matters for large textures, multi-sample anti-aliasing, or compute workloads that stream data through memory.

The Intel Arc G3 wins in compute throughput and power efficiency. Its FP32 of 6.144 TFLOPS exceeds the Pro A60M's 5.325 TFLOPS by 15.4%, and its FP16 of 12.29 TFLOPS exceeds the Pro A60M's 10.65 TFLOPS by the same margin. The G3 achieves this with a 25 W TDP, which is 73.7% lower than the Pro A60M's 95 W TDP. The G3's boost clock of 2400 MHz is 84.6% higher than the Pro A60M's 1300 MHz, which compensates for its lower unit counts. For shader-bound workloads like compute kernels, physics simulation, or general-purpose GPGPU tasks that rely on raw FP32 or FP16 throughput, the G3 has the edge.

The RT core counts favor the Pro A60M (16 versus 10), but no ray tracing benchmarks exist in the database to quantify that advantage. The G3's newer architecture (Xe3-LPG versus Xe-HPG) and smaller process node (3 nm versus 6 nm) may bring architectural efficiency improvements, but the data does not include any architectural efficiency measurements. The release dates show the G3 is nearly three years newer (May 2026 versus June 2023), which may imply newer feature support, but both share the same API levels: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

The use-case split is clear from the metrics: the Pro A60M is positioned for memory-intensive rendering and display workloads that require consistent bandwidth and high fill rates, while the G3 is positioned for compute-focused tasks that benefit from higher TFLOPS and lower power draw. The G3's system-shared memory means its real-world performance will vary with the host system's memory speed and capacity, a variable that the Pro A60M does not face. The Pro A60M's dedicated memory gives it a fixed performance envelope, while the G3's performance is contingent on platform integration.