Intel Arc 140V Mobile vs Intel Arc G3 Comparison

The Verdict

The recorded data presents two distinct mobile integrated graphics solutions from Intel, separated by architecture generation and design priorities. The Intel Arc 140V Mobile, based on Lunar Lake and the Xe2-LPG architecture, is the established part, released on 2024-09-23. The Intel Arc G3, based on Panther Lake and the Xe3-LPG architecture, is the newer part with a release date of 2026-05-31. Both are active production parts, and both sit at the 50th percentile against all GPUs in the database, though neither has recorded benchmark scores or nearest rivals to calibrate that position.

The Arc 140V Mobile is the higher-power part at 37 W, while the Arc G3 operates at a lower 25 W. This power difference is central to the analysis. The Arc 140V Mobile uses the Xe2-LPG architecture on a 3 nm TSMC process with a 172 mm² die. The Arc G3 uses the newer Xe3-LPG architecture on a 3 nm Intel process with an unknown die size. The G3 offers higher raw compute throughput: its FP32 rate of 6.144 TFLOPS exceeds the 140V Mobile's 3.994 TFLOPS by a substantial margin. The G3 also boosts higher at 2400 MHz versus 1950 MHz, and carries more shading units (1280 versus 1024) and more ray tracing cores (10 versus 8).

However, the 140V Mobile wins in other structural categories. It has 64 texture mapping units versus the G3's 40, and 32 ROPs versus the G3's 20. This gives the 140V Mobile a higher pixel rate of 62.40 GPixel/s and a higher texture rate of 124.8 GTexel/s, against the G3's 48.00 GPixel/s and 96.00 GTexel/s. The trade-off is clear: the G3 favors shader-heavy and ray-traced workloads, while the 140V Mobile favors rasterization throughput and fill-rate-bound tasks.

The verdict depends on the workload. For users whose tasks are dominated by pixel fill and texture filtering, the Arc 140V Mobile is the stronger choice per the data. For compute-heavy or ray-traced workloads, the Arc G3 delivers more raw FP32 and FP16 performance. The G3 does this at a lower 25 W TDP, which is notable for mobile integration. Both share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Neither has a launch MSRP recorded in the database.

Where Each One Wins

The Arc 140V Mobile wins in fill-rate and texture-throughput metrics. Its pixel rate of 62.40 GPixel/s is 30% higher than the G3's 48.00 GPixel/s. Its texture rate of 124.8 GTexel/s is 30% higher than the G3's 96.00 GTexel/s. These figures indicate that the 140V Mobile is better positioned for workloads that saturate render output units and texture units, such as traditional 3D rasterization at high resolutions or with heavy overdraw. The 140V Mobile also has a wider ROP and TMU configuration: 32 ROPs versus 20, and 64 TMUs versus 40.

The Arc G3 wins in compute throughput. Its FP32 rate of 6.144 TFLOPS is 54% higher than the 140V Mobile's 3.994 TFLOPS. Its FP16 rate of 12.29 TFLOPS (2:1) is 54% higher than the 140V Mobile's 7.987 TFLOPS (2:1). The G3 also has more shading units (1280 versus 1024) and more ray tracing cores (10 versus 8). The G3's boost clock of 2400 MHz is 23% higher than the 140V Mobile's 1950 MHz. This combination points to advantages in general-purpose GPU compute, shader-bound rendering, and ray-traced effects.

The power envelope separates the two further. The Arc G3 achieves its higher compute throughput at 25 W, which is 12 W lower than the 140V Mobile's 37 W. This suggests the G3 is the more efficient part for compute per watt, though the database does not record actual power draw measurements. The 140V Mobile uses more power to deliver its fill-rate advantages.

The memory subsystem is identical in configuration: both use System Shared memory with System Shared type, bus width, and System Dependent bandwidth. The database records no separate memory pool for either part. Display outputs are Portable Device Dependent for both.

Architecture Differences

The two parts come from different Intel mobile graphics generations. The Arc 140V Mobile belongs to Arc Graphics-M (Lunar Lake) and uses the Xe2-LPG architecture. The Arc G3 belongs to Arc Graphics-M (Panther Lake) and uses the Xe3-LPG architecture. This generation step is the primary architectural differentiator.

The manufacturing process differs by foundry. The 140V Mobile is fabricated by TSMC on a 3 nm process with a die size of 172 mm². The Arc G3 is fabricated by Intel on a 3 nm process with an unknown die size. Transistor counts are unknown for both parts, and transistor densities are not recorded.

Core configurations differ in several dimensions. The 140V Mobile has 1024 shading units, 64 TMUs, 32 ROPs, and 8 ray tracing cores. The Arc G3 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. The G3 has 25% more shading units and 25% more ray tracing cores. The 140V Mobile has 60% more TMUs and 60% more ROPs. Neither part has tensor cores recorded.

Clock behavior differs. Both have the same base clock of 300 MHz. The boost clock diverges: the G3 reaches 2400 MHz, while the 140V Mobile reaches 1950 MHz. The database records no game clock for either part.

The TDP values place the parts in different power classes. The 140V Mobile is rated at 37 W, the G3 at 25 W. The G3 lists no power connectors, consistent with its lower power envelope and IGP slot width. The 140V Mobile also uses an IGP slot width with no power connectors recorded. Both use an IGP bus interface.

Memory is shared with the system for both. Memory size, type, and bus width are all listed as System Shared, with bandwidth as System Dependent. This means actual memory performance depends on the host platform, which the database does not specify.

API support is identical: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The predecessor field differs: the 140V Mobile lists HD Graphics-M as its predecessor, while the G3 has no predecessor recorded. Neither part has a successor recorded.

FAQ

Q: Which GPU has higher raw compute performance?

A: The Intel Arc G3. Its FP32 rate is 6.144 TFLOPS and its FP16 rate is 12.29 TFLOPS (2:1). The Intel Arc 140V Mobile delivers 3.994 TFLOPS FP32 and 7.987 TFLOPS FP16 (2:1). The G3 is 54% ahead in both metrics.

Q: Which GPU has higher fill-rate performance?

A: The Intel Arc 140V Mobile. Its pixel rate is 62.40 GPixel/s and its texture rate is 124.8 GTexel/s. The Intel Arc G3 records 48.00 GPixel/s and 96.00 GTexel/s. The 140V Mobile is 30% ahead in both metrics.

Q: How do the power requirements compare?

A: The Intel Arc 140V Mobile is rated at 37 W TDP. The Intel Arc G3 is rated at 25 W TDP. The G3 uses 12 W less, while delivering higher FP32 and FP16 throughput.

Q: Do both GPUs support the same graphics APIs?

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

Q: What are the architecture and process differences?

A: The Arc 140V Mobile uses the Xe2-LPG architecture on the Lunar Lake chip, fabricated by TSMC on a 3 nm process with a 172 mm² die. The Arc G3 uses the Xe3-LPG architecture on the Panther Lake chip, fabricated by Intel on a 3 nm process with an unknown die size.

Q: How do the core configurations differ?

A: The Arc 140V Mobile has 1024 shading units, 64 TMUs, 32 ROPs, and 8 ray tracing cores. The Arc G3 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. The G3 has more shading units and ray tracing cores; the 140V Mobile has more TMUs and ROPs.

Head-to-Head Benchmarks

The database records no direct head-to-head benchmark scores, wins, or nearest rivals for either part. The comparison below is based on the recorded specification data, which functions as the measurable benchmark for these integrated GPUs.

The largest win for the Arc G3 is in FP32 throughput. At 6.144 TFLOPS, it is 54% ahead of the 140V Mobile's 3.994 TFLOPS. The FP16 result follows the same pattern: 12.29 TFLOPS versus 7.987 TFLOPS, also a 54% advantage. These are the most significant performance deltas in the recorded data. The G3's boost clock advantage of 2400 MHz versus 1950 MHz is a 23% difference, supporting its compute lead.

The largest win for the Arc 140V Mobile is in pixel rate. At 62.40 GPixel/s, it is 30% ahead of the G3's 48.00 GPixel/s. The texture rate follows: 124.8 GTexel/s versus 96.00 GTexel/s, also a 30% advantage. These wins come from the 140V Mobile's wider ROP and TMU counts: 32 ROPs versus 20, and 64 TMUs versus 40.

The core count comparison shows the G3's compute orientation. It has 1280 shading units against the 140V Mobile's 1024, a 25% advantage. Its 10 ray tracing cores against 8 is a 25% advantage. The 140V Mobile's TMU and ROP advantages are larger in percentage terms: 64 TMUs against 40 is a 60% advantage, and 32 ROPs against 20 is also a 60% advantage.

The power data adds context. The G3 delivers its 54% FP32 advantage at 25 W, while the 140V Mobile requires 37 W for its fill-rate advantages. The G3's compute efficiency per watt is not directly recorded, but the specification data shows a lower TDP with higher compute output. The 140V Mobile's fill-rate advantages come at a 12 W higher TDP.

Both parts share the same base clock of 300 MHz, the same memory configuration (System Shared), and the same API set. The die size difference is notable only for the 140V Mobile, which records 172 mm²; the G3's die size is unknown. The foundry difference (TSMC for the 140V Mobile, Intel for the G3) is recorded but does not translate into a measured performance difference in the database.

The release dates place these parts in different market positions. The 140V Mobile launched on 2024-09-23, while the G3 is dated 2026-05-31. Both are marked as Active in production status. The 140V Mobile lists HD Graphics-M as its predecessor; the G3 has no predecessor recorded.

In the absence of recorded benchmark scores, the specification deltas define the comparison. The Arc G3 is the compute-oriented part with higher FP32, FP16, shading units, ray tracing cores, and boost clock. The Arc 140V Mobile is the rasterization-oriented part with higher pixel rate, texture rate, TMUs, and ROPs. The 30% fill-rate advantage for the 140V Mobile and the 54% compute advantage for the G3 are the defining margins in this comparison.