How much VRAM does the Intel Arc Pro A40 6GB have?

The Intel Arc Pro A40 6GB has 6 GB of GDDR6 with 192 GB/s memory bandwidth.

What is the Intel Arc Pro A40 6GB best for?

With 6 GB of VRAM, the Intel Arc Pro A40 6GB is best for running compact models (1B–8B) at low quantization, suitable for edge inference, prototyping, and lightweight tasks.

What LLMs can the Intel Arc Pro A40 6GB run locally?

The Intel Arc Pro A40 6GB can run 19 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.1 8B Instruct at Q3_K_M, Llama 3.2 3B Instruct at Q8_0, Llama 3.2 1B Instruct at BF16.

Can the Intel Arc Pro A40 6GB run Llama 3.3 70B Instruct?

The Intel Arc Pro A40 6GB can run Llama 3.3 70B Instruct with CPU offload at Q2_K quantization, but inference will be slower than native VRAM execution.

Can the Intel Arc Pro A40 6GB run Qwen 3.6 27B?

The Intel Arc Pro A40 6GB can run Qwen 3.6 27B with CPU offload at Q6_K quantization, but inference will be slower than native VRAM execution.

Can the Intel Arc Pro A40 6GB run Llama 3.1 8B Instruct?

Yes. The Intel Arc Pro A40 6GB runs Llama 3.1 8B Instruct natively in VRAM at Q3_K_M quantization, achieving approximately 55.8 tokens per second.

Intel Arc Pro A40 6GB

The Intel Arc Pro A40 6GB has 6 GB VRAM and 192 GB/s memory bandwidth. It can run 19 of our 70 tracked models natively in VRAM at 8k context.

Intel Arc Pro A40 6GB: 2022 Xe-HPG workstation GPU with 6GB ECC GDDR6 at 192 GB/s — single-slot Arc Pro entry.

7B at Q4 natively; 6GB limits model selection. ~2-4 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	6 GB
Memory type	GDDR6
Memory bandwidth	192 GB/s
Compute backend	VULKAN
Tier	Workstation
Released	2022
Models (native)	19 / 70
Models (offload)	28 / 70

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

Models this GPU runs natively in VRAM (19)

Models that fit with CPU offload (28)

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

Too large for this GPU (23)

Frequently asked questions

How much VRAM does the Intel Arc Pro A40 6GB have?: The Intel Arc Pro A40 6GB has 6 GB of GDDR6 with 192 GB/s memory bandwidth.
What is the Intel Arc Pro A40 6GB best for?: With 6 GB of VRAM, the Intel Arc Pro A40 6GB is best for running compact models (1B–8B) at low quantization, suitable for edge inference, prototyping, and lightweight tasks.
What LLMs can the Intel Arc Pro A40 6GB run locally?: The Intel Arc Pro A40 6GB can run 19 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.1 8B Instruct at Q3_K_M, Llama 3.2 3B Instruct at Q8_0, Llama 3.2 1B Instruct at BF16.
Can the Intel Arc Pro A40 6GB run Llama 3.3 70B Instruct?: The Intel Arc Pro A40 6GB can run Llama 3.3 70B Instruct with CPU offload at Q2_K quantization, but inference will be slower than native VRAM execution.
Can the Intel Arc Pro A40 6GB run Qwen 3.6 27B?: The Intel Arc Pro A40 6GB can run Qwen 3.6 27B with CPU offload at Q6_K quantization, but inference will be slower than native VRAM execution.
Can the Intel Arc Pro A40 6GB run Llama 3.1 8B Instruct?: Yes. The Intel Arc Pro A40 6GB runs Llama 3.1 8B Instruct natively in VRAM at Q3_K_M quantization, achieving approximately 55.8 tokens per second.