How much VRAM does the Intel Arc A380 6GB have?

The Intel Arc A380 6GB has 6 GB of GDDR6 with 186 GB/s memory bandwidth.

What is the Intel Arc A380 6GB best for?

With 6 GB of VRAM, the Intel Arc A380 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 A380 6GB run locally?

The Intel Arc A380 6GB can run 23 of the 99 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Ornith 1.5 9B at Q3_K_M, Qwen 3.5 9B at Q3_K_M, Bonsai 27B at 1-bit (Q1_0).

Can the Intel Arc A380 6GB run Gemma 4 31B?

The Intel Arc A380 6GB 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 A380 6GB run Qwen 3.6 27B?

The Intel Arc A380 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 A380 6GB run Qwen3 8B?

Yes. The Intel Arc A380 6GB runs Qwen3 8B natively in VRAM at Q3_K_M quantization, achieving approximately 30.3 tokens per second.

Intel Arc A380 6GB

The Intel Arc A380 6GB has 6 GB VRAM and 186 GB/s memory bandwidth. It can run 23 of our 99 tracked models natively in VRAM at 8k context.

With 6 GB GDDR6, the Intel Arc A380 6GB is a consumer-tier GPU that can run 23 models natively.

Intel Arc A380 6GB: 2022 Xe-HPG Alchemist with 6GB GDDR6 at 186 GB/s, entry-level Arc discrete GPU.

3B-7B at Q4 with tight fit; 6GB cap rules out most 13B models. ~2-4 t/s for 7B via Vulkan.

Vulkan via llama.cpp works cross-platform. SYCL backend requires oneAPI toolkit. Ollama support limited.

Vendor	Intel
Architecture	Xe-HPG (Alchemist)
VRAM	6 GB
Memory type	GDDR6
Memory bandwidth	186 GB/s
Compute backend	VULKAN
Tier	Consumer
Released	2022
Models (native)	23 / 99
Models (offload)	31 / 99

Software: Vulkan backend works in llama.cpp; SYCL backend available but requires oneAPI toolkit. Ollama support is limited.

Need more than 6GB? Rent an RTX 3080 10GB from $0.17/hr ↗

Prices as of Oct 13, 2026. Rates change; check RunPod for current pricing. Affiliate link: CanItRun may earn a commission. Doesn't affect the fit calculation above.

Popular models for this GPU

Bonsai 27B Gemma 4 12B (Unified)Qwen 3.5 9B Ornith 1.5 9B Llama 3.1 8B Instruct

Models this GPU runs natively in VRAM (23)

Show 18 more

Models that fit with CPU offload (31)

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

Too large for this GPU (45)

Explore

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

Frequently asked questions

How much VRAM does the Intel Arc A380 6GB have?: The Intel Arc A380 6GB has 6 GB of GDDR6 with 186 GB/s memory bandwidth.
What is the Intel Arc A380 6GB best for?: With 6 GB of VRAM, the Intel Arc A380 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 A380 6GB run locally?: The Intel Arc A380 6GB can run 23 of the 99 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Ornith 1.5 9B at Q3_K_M, Qwen 3.5 9B at Q3_K_M, Bonsai 27B at 1-bit (Q1_0).
Can the Intel Arc A380 6GB run Gemma 4 31B?: The Intel Arc A380 6GB 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 A380 6GB run Qwen 3.6 27B?: The Intel Arc A380 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 A380 6GB run Qwen3 8B?: Yes. The Intel Arc A380 6GB runs Qwen3 8B natively in VRAM at Q3_K_M quantization, achieving approximately 30.3 tokens per second.