How much VRAM does the Intel Data Center GPU Max 1550 have?

The Intel Data Center GPU Max 1550 has 128 GB of HBM2e with 3276 GB/s memory bandwidth.

What is the Intel Data Center GPU Max 1550 best for?

With 128 GB of VRAM, the Intel Data Center GPU Max 1550 is a server-class GPU designed for running the largest open-weight models (70B–405B) at high quantization with ample context.

What LLMs can the Intel Data Center GPU Max 1550 run locally?

The Intel Data Center GPU Max 1550 can run 58 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.3 70B Instruct at Q8_0, Llama 3.1 8B Instruct at FP32, Llama 3.2 3B Instruct at FP32.

Can the Intel Data Center GPU Max 1550 run Llama 3.3 70B Instruct?

Yes. The Intel Data Center GPU Max 1550 runs Llama 3.3 70B Instruct natively in VRAM at Q8_0 quantization, achieving approximately 46.8 tokens per second.

Can the Intel Data Center GPU Max 1550 run Qwen 3.6 27B?

Yes. The Intel Data Center GPU Max 1550 runs Qwen 3.6 27B natively in VRAM at BF16 quantization, achieving approximately 60.7 tokens per second.

Can the Intel Data Center GPU Max 1550 run Llama 3.1 8B Instruct?

Yes. The Intel Data Center GPU Max 1550 runs Llama 3.1 8B Instruct natively in VRAM at FP32 quantization, achieving approximately 102.4 tokens per second.

Intel Data Center GPU Max 1550

The Intel Data Center GPU Max 1550 has 128 GB VRAM and 3276 GB/s memory bandwidth. It can run 58 of our 70 tracked models natively in VRAM at 8k context.

The Intel Data Center GPU Max 1550 is Intel's flagship HPC accelerator with 128GB of HBM2e at 3,276 GB/s — enough to run 70B models at Q8 or larger 100B+ models at lower quantization entirely in GPU memory. It targets HPC and AI training workloads in supercomputing clusters via Intel's oneAPI/SYCL stack.

Intel Data Center GPU Max 1550: 2022 Xe-HPC Ponte Vecchio with 128GB HBM2e at 3,276 GB/s — Intel's top HPC accelerator.

70B at Q8 or 100B+ at lower quantizations fit in 128GB. Highest Intel bandwidth for inference.

SYCL/oneAPI gives best performance; llama.cpp SYCL backend supported. Typically cloud/HPC-accessed.

Vendor	Intel
Architecture	Xe-HPC (Ponte Vecchio)
VRAM	128 GB
Memory type	HBM2e
Memory bandwidth	3276 GB/s
Compute backend	VULKAN
Tier	Datacenter
Released	2022
Models (native)	58 / 70
Models (offload)	3 / 70

Software: Typically accessed via cloud. Uses SYCL/oneAPI for best performance; llama.cpp SYCL backend supported.

Models this GPU runs natively in VRAM (58)

Models that fit with CPU offload (3)

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

Too large for this GPU (9)

Frequently asked questions

How much VRAM does the Intel Data Center GPU Max 1550 have?: The Intel Data Center GPU Max 1550 has 128 GB of HBM2e with 3276 GB/s memory bandwidth.
What is the Intel Data Center GPU Max 1550 best for?: With 128 GB of VRAM, the Intel Data Center GPU Max 1550 is a server-class GPU designed for running the largest open-weight models (70B–405B) at high quantization with ample context.
What LLMs can the Intel Data Center GPU Max 1550 run locally?: The Intel Data Center GPU Max 1550 can run 58 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.3 70B Instruct at Q8_0, Llama 3.1 8B Instruct at FP32, Llama 3.2 3B Instruct at FP32.
Can the Intel Data Center GPU Max 1550 run Llama 3.3 70B Instruct?: Yes. The Intel Data Center GPU Max 1550 runs Llama 3.3 70B Instruct natively in VRAM at Q8_0 quantization, achieving approximately 46.8 tokens per second.
Can the Intel Data Center GPU Max 1550 run Qwen 3.6 27B?: Yes. The Intel Data Center GPU Max 1550 runs Qwen 3.6 27B natively in VRAM at BF16 quantization, achieving approximately 60.7 tokens per second.
Can the Intel Data Center GPU Max 1550 run Llama 3.1 8B Instruct?: Yes. The Intel Data Center GPU Max 1550 runs Llama 3.1 8B Instruct natively in VRAM at FP32 quantization, achieving approximately 102.4 tokens per second.