In April, Intel said that it expected to generate revenue of $500 million from Gaudi 3 in 2024 — a paltry sum compared to the $4.5 billion AMD expects to rake in from sales of its Instinct MI300 ...

Intel says the new Gaudi 3 accelerator offers tangible performance advantages over Gaudi 2 and can even challenge Nvidia's H100 (at least when this GPU does not use sparsity) in some cases. It is ...

Intel, which suggested it would pull in $1 billion, even $2 billion on the back of AI, now says it won’t even meet its more modest $500 million goal for its Gaudi AI accelerator this year.

Gaudi 3 is the third iteration of an AI processor series that Intel obtained through a 2019 startup acquisition. The chip is based on Taiwan Semiconductor Manufacturing Co. Ltd.’s five-nanometer ...

But Gaudi 3 is not the only thing Intel is announcing. It has three new products to complement its next-gen chip. The first is the Intel Gaudi 3 AI Accelerator card HL-325L, which is OAM-compliant.

Gaudi 3 vs. Nvidia Intel wasted no time with AMD comparisons, preferring to tout their performance advantages vs. the Nvidia H100 and H200 for training and inference processing.

Compared to Nvidia's H100 chip, Intel projects a 50 percent faster training time on Gaudi 3 for both OpenAI's GPT-3 175B LLM and the 7-billion parameter version of Meta's Llama 2.

Intel just launched its Gaudi 3 accelerator to compete with Nvidia and AMD among enterprise IT customers looking for practicable ways to implement generative AI at scale.

Intel compared its new Gaudi 3 AI accelerator against NVIDIA's current-gen Hopper H100 and H200 AI GPUs, with Intel's in-house benchmarks have the Gaudi 3 being up to 1.7x faster for AI training ...

Intel says that its new Gaudi 3 AI accelerator offers up to 1856 BF16/FP8 matrix TFLOPS as well as up to 28.7 BF16 vector TFLOPS at around 600W TDP, which when compared to the NVIDIA H100 AI GPU ...

IBM and Intel on Thursday said IBM Cloud will begin offering Gaudi 3 to customers early next year. The chip’s accelerators will be available for both hybrid and on-premise environments, and IBM ...