CanItRun Logocanitrun.

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 71 tracked models natively in VRAM at 8k context.

With 128 GB HBM2e, the Intel Data Center GPU Max 1550 is a datacenter-tier GPU that can run 58 models natively. It handles 70B-class models at Q4 quantization.

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.

VendorIntel
ArchitectureXe-HPC (Ponte Vecchio)
VRAM128 GB
Memory typeHBM2e
Memory bandwidth3276 GB/s
Compute backendVULKAN
TierDatacenter
Released2022
Models (native)58 / 71
Models (offload)3 / 71
Software: Typically accessed via cloud. Uses SYCL/oneAPI for best performance; llama.cpp SYCL backend supported.

Popular models for this GPU

DeepSeek V4 Flash 284BQwen3 235B-A22B (MoE)MiniMax M2.5 229BMiniMax M2.7 229BMixtral 8x22B Instruct v0.1

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 (10)

Models mentioned

DeepSeek V4 Flash 284B284B (13B active)
DeepSeekQ2_K rec.
Qwen3 235B-A22B (MoE)235B (22B active)
AlibabaQ2_K rec.
MiniMax M2.5 229B229B (10B active)
MiniMaxQ2_K rec.
MiniMax M2.7 229B229B (10B active)
MiniMaxQ2_K rec.
Mixtral 8x22B Instruct v0.1141B (39B active)
Mistral AIQ4_K_M rec.
Qwen 3.5 122B-A10B (MoE)122B (10B active)
AlibabaQ3_K_M rec.
Nemotron 3 Super 120B120B (12B active)
NVIDIAQ3_K_M rec.
GPT-OSS 120B117B (5B active)
OpenAIQ4_K_M rec.
Llama 4 Scout 109B109B (17B active)
MetaQ4_K_M rec.
GLM-4.5 Air 106B106B (12B active)
Z.aiQ3_K_M rec.
GLM-4.6V 106B106B (12B active)
Z.aiQ3_K_M rec.
Qwen 2.5 72B Instruct72B
AlibabaQ4_K_M rec.
Llama 3.3 70B Instruct70B
MetaQ4_K_M rec.
DeepSeek R1 Distill Llama 70B70B
DeepSeekQ4_K_M rec.
Llama 3.1 70B Instruct70B
MetaQ4_K_M rec.
Mixtral 8x7B Instruct v0.146.7B (12.9B active)
Mistral AIQ4_K_M rec.
Command-R 35B35B
CohereQ4_K_M rec.
Qwen 3.5 35B-A3B (MoE)35B (3B active)
AlibabaQ4_K_M rec.
Qwen 3.6 35B35B
AlibabaQ4_K_M rec.
Yi 1.5 34B Chat34.4B
01.AIQ4_K_M rec.
Qwen3 32B32.8B
AlibabaQ4_K_M rec.
Qwen 2.5 32B Instruct32.5B
AlibabaQ4_K_M rec.
Qwen 2.5 Coder 32B Instruct32.5B
AlibabaQ4_K_M rec.
DeepSeek R1 Distill Qwen 32B32.5B
DeepSeekQ4_K_M rec.
Nemotron 3 Nano 30B32B (3B active)
NVIDIAQ5_K_M rec.
Gemma 4 31B31B
GoogleQ4_K_M rec.
Qwen3 30B-A3B (MoE)30B (3B active)
AlibabaQ4_K_M rec.
Gemma 2 27B Instruct27.2B
GoogleQ4_K_M rec.
Gemma 3 27B Instruct27B
GoogleQ4_K_M rec.
Qwen 3.6 27B27B
AlibabaQ4_K_M rec.
Gemma 4 26B (MoE)26B (3.8B active)
GoogleQ4_K_M rec.
Mistral Small 3.1 24B Instruct24B
Mistral AIQ4_K_M rec.
Mistral Small 22B22.2B
Mistral AIQ4_K_M rec.
GPT-OSS 20B21B (4B active)
OpenAIQ5_K_M rec.
Qwen3 14B14.8B
AlibabaQ5_K_M rec.
Qwen 2.5 14B Instruct14.7B
AlibabaQ5_K_M rec.
Phi-4 14B Instruct14B
MicrosoftQ5_K_M rec.
Mistral Nemo 12B Instruct12.2B
Mistral AIQ5_K_M rec.
Gemma 3 12B Instruct12.2B
GoogleQ5_K_M rec.
Gemma 2 9B Instruct9.2B
GoogleQ5_K_M rec.
Llama 3.1 8B Instruct8B
MetaQ5_K_M rec.
DeepSeek R1 Distill Llama 8B8B
DeepSeekQ5_K_M rec.
Qwen3 8B8B
AlibabaQ5_K_M rec.
Qwen 2.5 7B Instruct7.6B
AlibabaQ6_K rec.
Mistral 7B Instruct v0.37.25B
Mistral AIQ6_K rec.
Gemma 3 4B Instruct4B
GoogleQ6_K rec.
Gemma 4 E4B4B
GoogleQ5_K_M rec.
Phi-3.5 Mini Instruct3.8B
MicrosoftQ6_K rec.
Llama 3.2 3B Instruct3.2B
MetaQ6_K rec.
Qwen 2.5 3B Instruct3.1B
AlibabaQ6_K rec.
Gemma 2 2B Instruct2.6B
GoogleQ8_0 rec.
Gemma 4 E2B2B
GoogleQ8_0 rec.
SmolLM2 1.7B Instruct1.7B
Hugging FaceQ8_0 rec.
Qwen 2.5 1.5B Instruct1.5B
AlibabaQ8_0 rec.
Llama 3.2 1B Instruct1.24B
MetaQ8_0 rec.
Gemma 3 1B Instruct1B
GoogleQ8_0 rec.
Qwen 2.5 0.5B Instruct0.5B
AlibabaQ8_0 rec.
SmolLM2 360M Instruct0.36B
Hugging FaceQ8_0 rec.

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 71 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.