The Intel Core Ultra 7 165HL uses the LGA 1851 socket and is built on a 7nm semiconductor process, with a maximum operating temperature rated at 105°C. It carries a Thermal Design Power of 45W and includes integrated graphics, making it a self-contained solution without requiring a discrete GPU. The processor supports 64-bit computing and interfaces with peripherals through PCIe 4, providing the bandwidth needed for modern storage and expansion devices.
The Core Ultra 7 165HL employs big.LITTLE technology, combining six cores running at 1.4 GHz with eight cores at 0.9 GHz, yielding a total of 22 threads across the hybrid layout. The processor can reach a turbo clock speed of 5 GHz under boosted conditions, while the clock multiplier sits at 14 — and the multiplier is locked, meaning manual overclocking is not supported. A 24MB L3 cache backs the core complex, helping to reduce memory latency during sustained workloads.
The integrated GPU in this processor is the Arc Xe-LPG 128EU, built around 128 execution units that back 1024 shading units, 64 texture mapping units, and 32 render output units. It operates at a base clock of 300 MHz and can reach a turbo frequency of 2300 MHz, with support for up to four displays simultaneously. On the API side, it is fully compatible with DirectX 12 Ultimate, alongside OpenGL 4.6 and OpenCL 3, covering a broad range of graphics and compute workloads.
The Core Ultra 7 165HL supports DDR5 memory at speeds up to 5600 MHz across a dual-channel configuration, offering a combined bandwidth ceiling suited to memory-intensive tasks. The processor can address up to 96GB of RAM in total, giving it meaningful headroom for demanding workloads. ECC memory, however, is not supported, which is a consideration for applications that require error-correcting memory for data integrity.
The Core Ultra 7 165HL supports multithreading and includes the NX bit for hardware-level execution protection against certain classes of malicious code. Its instruction set support spans MMX, F16C, FMA3, AES, AVX, AVX2, SSE 4.1, and SSE 4.2, covering a wide range of compute tasks including floating-point operations, hardware-accelerated encryption, and vectorized data processing workloads.