Intel Arc Pro B60 (24GB)

The Intel Arc Pro B60 steps up from the B50 to 24GB of memory on the same Xe2 “Battlemage” architecture. It is aimed at AI inference, generative design and 3D workloads where memory capacity matters as much as raw compute. Intel does not manufacture a reference-design B60: every card ships from a board partner (ASRock, Sparkle and others) built to Intel’s reference specification, so this listing is a partner card faithful to that spec rather than an Intel-branded reference board.

Who it's for

• Running quantized LLMs in the 13B–34B range locally
• Larger diffusion and vision models that would not fit in a 12GB or 16GB card
• Professional visualization, CAD and generative design with dense 3D scenes and high-resolution textures
• Teams that want an affordable path to 48GB of pooled memory by pairing two cards

Key features

• 24GB GDDR6 on a 192-bit bus: up to 456GB/s of bandwidth, well ahead of most cards in its price class, enough to hold large quantized AI models or complex 3D scenes entirely in VRAM.
• 20 Xe2 cores, 160 XMX engines: a step up from the B50’s core count, with 20 dedicated ray tracing units for professional visualization work.
• 197 TOPS INT8 AI performance: dedicated matrix acceleration for the low-precision math that dominates modern LLM and vision-model inference.
• 12.28 TFLOPS FP32 compute: solid general shader performance for CAD, rendering and design applications.
• Multi-GPU ready: pairs of B60 cards can combine (Intel’s “Battlemage” dual-GPU and Project Battlematrix configurations) to pool up to 48GB of addressable memory for larger models.
• PCIe 5.0 x8 interface: modern interface bandwidth with efficient, scalable power delivery.
• 120-200W total board power: a wide, partner-dependent envelope that lets board vendors tune for efficiency or maximum clocks.

Specifications

Good to know

• Because every B60 ships from a board partner, exact clocks, cooling and connector layout vary slightly by vendor. All cards adhere to Intel’s core specification above.
• Intel’s software ecosystem is newer than CUDA’s. oneAPI, OpenVINO and the driver stack support mainstream AI and CAD frameworks, but bleeding-edge research code that assumes NVIDIA hardware will need more setup work.
• Standard, well-supported tools such as llama.cpp, PyTorch with Intel extensions, OpenVINO-based inference and mainstream CAD applications are the comfortable fit.
• Intel has been expanding ISV certifications and driver validation for the Arc Pro line.

Choose the B60 over the B50 when 24GB of memory is the deciding factor for your models or scenes. Choose a CUDA card instead if your code assumes NVIDIA hardware.