Intel Arc Pro A60 vs NVIDIA GeForce RTX 4060 Ti AD104 Comparison

# FAQ

Q: How do the two GPUs compare in raw compute performance?

A: The NVIDIA GeForce RTX 4060 Ti AD104 delivers 22.06 TFLOPS FP32 performance, while the Intel Arc Pro A60 provides 8.397 TFLOPS. This gives the NVIDIA card roughly 2.6 times the raw single-precision throughput.

Q: What are the memory configurations of each card?

A: The Intel Arc Pro A60 uses 12 GB of GDDR6 memory on a 192-bit bus with 384.0 GB/s bandwidth. The NVIDIA GeForce RTX 4060 Ti AD104 has 8 GB of GDDR6 on a 128-bit bus with 288.0 GB/s bandwidth.

Q: Which card has a higher pixel fill rate?

A: The Intel Arc Pro A60 achieves 131.2 GPixel/s, which is higher than the NVIDIA card's 121.7 GPixel/s, despite the NVIDIA card having substantially higher compute throughput.

Q: How do the transistor counts differ between the two architectures?

A: The NVIDIA AD104 chip packs 35,800 million transistors on a 294 mm² die, while Intel's DG2-256 contains 11,500 million transistors on a 269 mm² die. The NVIDIA chip achieves a much higher transistor density of 121.8M per mm² versus Intel's 42.8M per mm².

Q: What is the production status of each GPU?

A: The Intel Arc Pro A60 is listed as Active in production, while the NVIDIA GeForce RTX 4060 Ti AD104 is marked End-of-life.

Q: Do both cards support the same API feature levels?

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

# Architecture Differences

The Intel Arc Pro A60 and NVIDIA GeForce RTX 4060 Ti AD104 represent fundamentally different approaches to GPU design, built on distinct architectures and manufacturing processes.

Intel's Arc Pro A60 uses the DG2-256 chip based on the Xe-HPG architecture, belonging to the Alchemist (Pro Series) generation. This chip is fabricated on a 6 nm process at TSMC, with 11,500 million transistors packed into a 269 mm² die. The transistor density works out to 42.8 million transistors per square millimeter. The Xe-HPG architecture is Intel's first dedicated discrete GPU architecture, designed specifically for gaming and professional workloads.

NVIDIA's GeForce RTX 4060 Ti AD104 uses the AD104 chip based on the Ada Lovelace architecture, part of the GeForce 40 generation. This chip is fabricated on a 5 nm process, also at TSMC, but with a dramatically higher transistor count: 35,800 million transistors on a 294 mm² die. The transistor density reaches 121.8 million per square millimeter, nearly three times Intel's density. Ada Lovelace introduced significant architectural changes including new RT cores and tensor cores.

The memory subsystems differ substantially. Intel pairs its chip with 12 GB of GDDR6 memory running at 2000 MHz with 16 Gbps effective speed on a 192-bit bus, yielding 384.0 GB/s bandwidth. NVIDIA uses 8 GB of GDDR6 at 2250 MHz with 18 Gbps effective speed on a 128-bit bus, producing 288.0 GB/s bandwidth. Intel's wider bus provides 33% more bandwidth, while NVIDIA's faster memory clock partially compensates for the narrower interface.

Both architectures implement hardware ray tracing, but with different approaches. Intel provides 16 RT cores, while NVIDIA includes 34 RT cores. NVIDIA also integrates 136 tensor cores, which are absent from Intel's specification. These tensor cores accelerate AI workloads and enable features like DLSS, a capability Intel's card does not replicate.

The shading resources also differ significantly. NVIDIA's AD104 includes 4352 shading units, 136 texture mapping units, and 48 ROPs. Intel's DG2-256 includes 2048 shading units, 128 TMUs, and 64 ROPs. Intel's higher ROP count contributes to its pixel fill rate advantage, while NVIDIA's larger shader array drives its compute advantage.

Clock speeds show a clear NVIDIA advantage. The RTX 4060 Ti AD104 runs at a 2310 MHz base clock and 2535 MHz boost clock, while the Arc Pro A60 operates at 900 MHz base and 2050 MHz boost. NVIDIA's higher clocks, combined with the larger shader count, account for the massive FP32 throughput gap.

The power delivery and board design also differ. Intel specifies a 130 W TDP with a 300 W suggested PSU and single-slot form factor. NVIDIA specifies 160 W TDP with a 450 W suggested PSU, dual-slot width, and requires a 16-pin power connector. NVIDIA's card measures 240 mm in length, 111 mm in height, and 40 mm in width, while Intel's dimensions are not listed.

Display outputs show another divergence: Intel provides 4x DisplayPort 2.0, while NVIDIA offers 1x HDMI 2.1 and 3x DisplayPort 1.4a. The bus interface differs too, with Intel using PCIe 4.0 x16 and NVIDIA using PCIe 4.0 x8.

# Head-to-Head Benchmarks

The benchmark database contains limited direct head-to-head results for these two cards. The Intel Arc Pro A60 has recorded benchmark scores, while the NVIDIA GeForce RTX 4060 Ti AD104 has no benchmark entries in the database. This asymmetry requires careful interpretation of the available data.

Focusing on the Intel Arc Pro A60's recorded performance, the card achieves a Geekbench OpenCL score of 63485 and a Geekbench Vulkan score of 57166. The average benchmark score across all tests is 60326. This places the Intel card at the 88th percentile among all GPUs in the database.

Examining the nearest rivals for the Intel Arc Pro A60 provides context for its performance position. The NVIDIA GeForce RTX 4090, with an average score of 60347, sits essentially tied with the Intel card, showing a delta of 0%. The AMD Radeon Pro Vega 48 scores 60140, just 0.3% behind. The AMD Radeon Pro W6600M scores 61896, which is 2.5% ahead of the Intel card. The AMD Radeon PRO V710 scores 58657, trailing by 2.8%.

These comparisons show that the Intel Arc Pro A60 occupies a performance tier comparable to high-end desktop GPUs despite its professional positioning. The near-tie with the RTX 4090 in average benchmark score is notable, though the two GPUs likely excel in different workload types.

Since the NVIDIA GeForce RTX 4060 Ti AD104 has no recorded benchmarks and no nearest rivals in the database, direct numerical comparison between the two cards is not possible from the available data. The specification differences provide the only basis for comparative analysis.

The FP32 compute figures suggest the NVIDIA card should substantially outperform the Intel card in compute-heavy workloads. At 22.06 TFLOPS versus 8.397 TFLOPS, the RTX 4060 Ti AD104 has approximately 2.6 times the raw single-precision throughput. Similarly, the texture fill rate of 344.8 GTexel/s for NVIDIA versus 262.4 GTexel/s for Intel indicates a 31% advantage for the NVIDIA card.

However, the pixel fill rate tells a different story. Intel's 131.2 GPixel/s exceeds NVIDIA's 121.7 GPixel/s by about 8%. This advantage stems from Intel's higher ROP count (64 versus 48) and its higher pixel clock output. For rasterization-heavy workloads that stress pixel output, the Intel card may hold an edge.

The memory bandwidth comparison favors Intel by a wider margin. Intel's 384.0 GB/s versus NVIDIA's 288.0 GB/s represents a 33% bandwidth advantage. Combined with 12 GB versus 8 GB capacity, the Intel card has clear advantages in memory-bound scenarios, particularly at higher resolutions or with large textures.

The RT core comparison shows NVIDIA with more than double Intel's count (34 versus 16), and NVIDIA's tensor cores add capabilities Intel lacks entirely. For ray tracing and AI-accelerated workloads, the NVIDIA architecture appears significantly more capable.

The production status difference matters for procurement decisions: Intel's card remains Active while NVIDIA's is End-of-life. The NVIDIA card's predecessor is listed as GeForce 30 and successor as GeForce 50, indicating it belongs to a transitional generation.

# Specification Differences

The two cards differ across nearly every specification category. The following comparison highlights only the fields where the two differ.

Chip and Architecture: Intel uses DG2-256 with Xe-HPG architecture from the Alchemist (Pro Series) generation. NVIDIA uses AD104 with Ada Lovelace architecture from the GeForce 40 generation.

Manufacturing: Intel uses a 6 nm process; NVIDIA uses 5 nm. Both use TSMC as the foundry.

Transistors: Intel has 11,500 million; NVIDIA has 35,800 million.

Die Size: Intel measures 269 mm²; NVIDIA measures 294 mm².

Transistor Density: Intel achieves 42.8M per mm²; NVIDIA achieves 121.8M per mm².

Clock Speeds: Intel runs at 900 MHz base and 2050 MHz boost. NVIDIA runs at 2310 MHz base and 2535 MHz boost. Memory clocks differ as well: Intel at 2000 MHz with 16 Gbps effective, NVIDIA at 2250 MHz with 18 Gbps effective.

Memory: Intel provides 12 GB GDDR6 on a 192-bit bus with 384.0 GB/s bandwidth. NVIDIA provides 8 GB GDDR6 on a 128-bit bus with 288.0 GB/s bandwidth.

Shading Units: Intel has 2048; NVIDIA has 4352.

TMUs: Intel has 128; NVIDIA has 136.

ROPs: Intel has 64; NVIDIA has 48.

RT Cores: Intel has 16; NVIDIA has 34.

Tensor Cores: Intel has none; NVIDIA has 136.

Pixel Rate: Intel achieves 131.2 GPixel/s; NVIDIA achieves 121.7 GPixel/s.

Texture Rate: Intel achieves 262.4 GTexel/s; NVIDIA achieves 344.8 GTexel/s.

FP32 Performance: Intel delivers 8.397 TFLOPS; NVIDIA delivers 22.06 TFLOPS.

FP16 Performance: Intel delivers 16.79 TFLOPS with a 2:1 ratio; NVIDIA delivers 22.06 TFLOPS with a 1:1 ratio.

TDP: Intel specifies 130 W; NVIDIA specifies 160 W.

Slot Width: Intel is single-slot; NVIDIA is dual-slot.

Power Connectors: Intel lists none; NVIDIA requires 1x 16-pin.

Suggested PSU: Intel recommends 300 W; NVIDIA recommends 450 W.

Bus Interface: Intel uses PCIe 4.0 x16; NVIDIA uses PCIe 4.0 x8.

Display Outputs: Intel provides 4x DisplayPort 2.0; NVIDIA provides 1x HDMI 2.1 and 3x DisplayPort 1.4a.

Dimensions: NVIDIA measures 240 mm length, 111 mm height, and 40 mm width. Intel's dimensions are not listed.

Production Status: Intel is Active; NVIDIA is End-of-life.

Release Date: Intel released on 2023-06-05; NVIDIA released on 2024-03-31.

Predecessor and Successor: Intel lists neither; NVIDIA lists GeForce 30 as predecessor and GeForce 50 as successor.

Launch MSRP: NVIDIA launched at 399 USD; Intel has no recorded launch MSRP.

Benchmark Data: Intel has two recorded benchmark scores; NVIDIA has none.

Percentile and Rivals: Intel sits at the 88th percentile with four nearest rivals; NVIDIA sits at the 50th percentile with no nearest rivals.

# The Verdict

The data presents two GPUs with fundamentally different strengths and positioning. The Intel Arc Pro A60 offers a professional-oriented feature set with active production status, while the NVIDIA GeForce RTX 4060 Ti AD104 targets the consumer GeForce market and has reached end-of-life status.

For compute-intensive workloads, the NVIDIA card holds a decisive advantage based on specification data. The 22.06 TFLOPS FP32 throughput versus Intel's 8.397 TFLOPS indicates the NVIDIA card can process roughly 2.6 times as many floating-point operations per second. The texture fill rate advantage (344.8 versus 262.4 GTexel/s) and the presence of 136 tensor cores further reinforce NVIDIA's position for tasks that leverage these resources.

The Intel card counters with advantages in memory bandwidth (384.0 GB/s versus 288.0 GB/s) and capacity (12 GB versus 8 GB). For workloads that stress memory throughput or require large working sets, the Intel card provides more headroom. The pixel fill rate advantage (131.2 versus 121.7 GPixel/s) also gives Intel an edge in certain rasterization scenarios.

The benchmark data available for the Intel card places it near the top of the database at the 88th percentile, with an average score essentially tied with the NVIDIA GeForce RTX 4090. This suggests the Arc Pro A60 performs at a level competitive with high-end consumer GPUs in the tested workloads, despite its lower compute specification.

Users prioritizing maximum compute throughput, ray tracing performance, or AI acceleration should look toward the NVIDIA GeForce RTX 4060 Ti AD104, as its specification data supports superiority in these areas. The card's 399 USD launch MSRP provides reference pricing, though its end-of-life status may affect availability.

Users needing larger memory capacity, higher memory bandwidth, or a professional card with active production support should consider the Intel Arc Pro A60. Its 12 GB memory capacity and 384.0 GB/s bandwidth exceed the NVIDIA card's specifications, and its DisplayPort 2.0 outputs support modern display connectivity.

The production status difference carries practical implications. Intel's Active status suggests ongoing availability and support, while NVIDIA's End-of-life status indicates the product has been superseded. The NVIDIA card's successor is listed as GeForce 50, confirming the platform transition.

The absence of benchmark data for the NVIDIA card limits direct performance comparison. The recorded data shows the Intel card's position among its nearest rivals, but no such data exists for the NVIDIA card. Specification-based analysis must therefore carry the comparative weight.

For power-constrained environments, the Intel card's 130 W TDP and 300 W suggested PSU offer lower system requirements than NVIDIA's 160 W TDP and 450 W suggested PSU. The single-slot form factor of the Intel card also accommodates space-constrained builds, whereas NVIDIA requires dual-slot spacing.

The API support matches across both cards (DirectX 12 Ultimate, OpenGL 4.6, Vulkan 1.4), ensuring similar software compatibility at the API level. The bus interface differs, with Intel using the full x16 width versus NVIDIA's x8, though both operate at PCIe 4.0 speeds.

The data supports distinct use cases for each card. The NVIDIA GeForce RTX 4060 Ti AD104 appears better suited for compute-heavy, AI-accelerated, or ray-traced workloads where its higher FP32 throughput, tensor cores, and larger RT core count provide clear specification advantages. The Intel Arc Pro A60 appears better suited for memory-intensive professional workloads, multi-display configurations, or environments requiring lower power consumption and single-slot installation.