In a bid to reduce its GPU costs amid an unprecedented component shortage, Meta is on track to begin manufacturing the latest versions of its AI-specific chip in September, Reuters reported, citing an internal memo.

At least one chip passed its testing phase in about six weeks, according to the memo. Meta is working with Broadcom on the chip design, but will use Taiwan Semiconductor Manufacturing Company (TSMC) to manufacture them. It is also purchasing RAM from Samsung, storage from Sandisk, and fiber optic equipment from Sumitomo Electric, according to the report.

Meta in March detailed the four new chips, developed under its Meta Training and Inference Accelerator (MTIA) program, some of which are currently in deployment or will be deployed this year or next. The company is taking a modular approach to designing these chips, anticipating that its needs will change as AI evolves rapidly when the chips are in production.

“Each generation of MTIA builds on the previous one, uses modular chiplets, incorporates the latest insights into AI workloads and hardware technologies, and is deployed at a shorter cadence,” the company wrote at the time.

The chips are expected to help the company save on purchasing GPUs from chipmakers like Nvidia and AMD, although it still expects to spend big with those suppliers as well, Reuters reports. Meta intends to use MTIA chips to train models for its classification and recommendation algorithms, broader AI workloads, and targeted inferences for its applications. The social media company has been producing its own AI chips since 2023.

Meta has been spending heavily to secure enough computing power to power its various AI efforts. In April, the company said it expects capital expenditures between $125 billion and $145 billion this year, much of which will go toward its AI efforts.

The company has been striking data center and power deals around the world, spending tens of billions to secure the computing capacity to train and deploy its new Muse Spark series of AI models. It plans to deploy 7 gigawatts of computing this year and double that amount next year, according to Reuters, which cited the memo.

It also signed a deal with ARM last year to secure computing for its recommendation systems, in addition to a multi-million dollar deal with AMD for its Instinct GPUs and a multi-million dollar deal with Amazon to use the cloud giant’s on-premise CPUs for AI-related needs.

Meta is not the only company trying to stem the tide of capital going to Nvidia. OpenAI last month unveiled an inference processor it is building with Broadcom, and Anthropic is said to be considering developing its own chips with Samsung. Amazon and Google develop their own chips for AI training and inference, and there are a host of startups being built in the space to meet growing demand.

Meta declined to comment.