How much VRAM does the Intel Arc Pro A60 12GB have?

The Intel Arc Pro A60 12GB has 12 GB of GDDR6 with 384 GB/s memory bandwidth.

What is the Intel Arc Pro A60 12GB best for?

With 12 GB of VRAM, the Intel Arc Pro A60 12GB comfortably handles 7B–8B models and can stretch to some 13B–14B models at aggressive quantization, a solid entry point into local LLM inference.

What LLMs can the Intel Arc Pro A60 12GB run locally?

The Intel Arc Pro A60 12GB can run 30 of the 94 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Ornith 1.5 9B at Q8_0, Gemma 4 26B (MoE) at Q2_K, Qwen 3.5 9B at Q8_0.

Can the Intel Arc Pro A60 12GB run Gemma 4 31B?

The Intel Arc Pro A60 12GB can run Gemma 4 31B with CPU offload at Q6_K quantization, but inference will be slower than native VRAM execution.

Can the Intel Arc Pro A60 12GB run Qwen 3.6 27B?

The Intel Arc Pro A60 12GB can run Qwen 3.6 27B with CPU offload at Q8_0 quantization, but inference will be slower than native VRAM execution.

Can the Intel Arc Pro A60 12GB run Qwen3 8B?

Yes. The Intel Arc Pro A60 12GB runs Qwen3 8B natively in VRAM at Q8_0 quantization, achieving approximately 25.7 tokens per second.

Intel Arc Pro A60 12GB

The Intel Arc Pro A60 12GB has 12 GB VRAM and 384 GB/s memory bandwidth. It can run 30 of our 94 tracked models natively in VRAM at 8k context.

With 12 GB GDDR6, the Intel Arc Pro A60 12GB is a workstation-tier GPU that can run 30 models natively. It handles 13B-class models comfortably.

The Intel Arc Pro A60 is a professional workstation GPU with 12GB of ECC-capable GDDR6 and ISV certifications for CAD and media workflows. For LLM inference it fits 7B models at Q8 or 13B models at Q4, with the Vulkan backend providing usable throughput. It targets workstations running mixed professional and AI inference workloads.

Intel Arc Pro A60 12GB: 2023 Xe-HPG workstation GPU with 12GB ECC GDDR6 at 512 GB/s, ISV-certified professional card.

7B at Q8 or 13B at Q4 natively. ~5-8 t/s for 7B via Vulkan.

Vulkan via llama.cpp works cross-platform. SYCL backend available with oneAPI. Primarily a professional workstation card.

Vendor	Intel
Architecture	Xe-HPG (Alchemist)
VRAM	12 GB
Memory type	GDDR6
Memory bandwidth	384 GB/s
Compute backend	VULKAN
Tier	Workstation
Released	2023
Models (native)	30 / 94
Models (offload)	27 / 94

Software: Vulkan backend works in llama.cpp; SYCL backend available with oneAPI toolkit. Primarily a workstation/professional card.

Popular models for this GPU

Bonsai 27B Gemma 4 26B (MoE)Qwen3 14B Qwen 2.5 14B Instruct Phi-4 14B Instruct

Models this GPU runs natively in VRAM (30)

Show 25 more

Models that fit with CPU offload (27)

These use system RAM for layers that don't fit in VRAM, so expect much slower inference.

Too large for this GPU (37)

Explore

Browse all guides →Browse all models →Browse all GPUs →

Frequently asked questions

How much VRAM does the Intel Arc Pro A60 12GB have?: The Intel Arc Pro A60 12GB has 12 GB of GDDR6 with 384 GB/s memory bandwidth.
What is the Intel Arc Pro A60 12GB best for?: With 12 GB of VRAM, the Intel Arc Pro A60 12GB comfortably handles 7B–8B models and can stretch to some 13B–14B models at aggressive quantization, a solid entry point into local LLM inference.
What LLMs can the Intel Arc Pro A60 12GB run locally?: The Intel Arc Pro A60 12GB can run 30 of the 94 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Ornith 1.5 9B at Q8_0, Gemma 4 26B (MoE) at Q2_K, Qwen 3.5 9B at Q8_0.
Can the Intel Arc Pro A60 12GB run Gemma 4 31B?: The Intel Arc Pro A60 12GB can run Gemma 4 31B with CPU offload at Q6_K quantization, but inference will be slower than native VRAM execution.
Can the Intel Arc Pro A60 12GB run Qwen 3.6 27B?: The Intel Arc Pro A60 12GB can run Qwen 3.6 27B with CPU offload at Q8_0 quantization, but inference will be slower than native VRAM execution.
Can the Intel Arc Pro A60 12GB run Qwen3 8B?: Yes. The Intel Arc Pro A60 12GB runs Qwen3 8B natively in VRAM at Q8_0 quantization, achieving approximately 25.7 tokens per second.