RunLocalAI
intel
GPU
128GB VRAM
workstation

Intel Gaudi 3

Intel's enterprise AI accelerator. 128GB HBM2e. Habana stack required — limited ecosystem support.

Released 2024

Overview

Intel's enterprise AI accelerator. 128GB HBM2e. Habana stack required — limited ecosystem support.

Specs

VRAM128 GB
Power draw900 W
Released2024
MSRP$18000
Backends

Models that fit

Open-weight models small enough to run on Intel Gaudi 3 with usable context.

Llama 3.1 8B Instruct
8B · llama
Qwen 3 30B-A3B
30B · qwen
Qwen 2.5 Coder 32B Instruct
32B · qwen
Llama 3.3 70B Instruct
70B · llama
Qwen 3 32B
32B · qwen
Gemma 4 31B Dense
31B · gemma
Qwen 3 8B
8B · qwen
DeepSeek R1 Distill Llama 70B
70B · deepseek

Frequently asked

What models can Intel Gaudi 3 run?

With 128GB VRAM, the Intel Gaudi 3 runs 70B models in 4-bit quantization, plus everything smaller. See the model list below for tested combinations.

Does Intel Gaudi 3 support CUDA?

Intel Gaudi 3 does not support CUDA. Use Vulkan-compatible tools (llama.cpp Vulkan backend) or check vendor-specific runtimes.

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify hardware specifications.