Anthropic in early talks to buy DRAM-less AI inference chips from UK startup — Fractile's SRAM architecture reduces need for pricey memory during extreme pricing and shortage crunch
The Claude developer is exploring a fourth chip supplier alongside Nvidia, Google, and Amazon.
Anthropic has reportedly held early discussions with London-based chip startup Fractile about purchasing the company's inference accelerators, The Information reported on Friday, citing people familiar with the matter. The talks would add Fractile as a fourth source of AI server silicon for the Claude developer, which already uses chips from Nvidia, Google, and Amazon.
Fractile's chips aren’t expected to reach commercial readiness until around 2027, placing any deployment well outside Anthropic's near-term procurement plans and roughly inside the same window as its Google-Broadcom TPU partnership.
Founded in 2022 by Oxford PhD Walter Goodwin, Fractile is developing an inference chip that co-locates memory and compute on the same die using SRAM rather than shuttling data to separate DRAM chips. That data movement between the GPU and off-chip DRAM is one of the main bottlenecks in running large AI models at speed.
Goodwin told Fortune in July 2024 that Fractile's design stores data needed for computations directly next to the transistors that perform the arithmetic, rather than relying on off-chip DRAM. Based on simulations at the time, Goodwin said Fractile could run a large language model 100 times faster and 10 times cheaper than Nvidia's GPUs, though the company had not yet manufactured test chips.
The company raised $15 million in seed funding, co-led by Kindred Capital, the NATO Innovation Fund, and Oxford Science Enterprises. Fractile is now in talks to raise $200 million at a $1 billion-plus valuation, with Founders Fund, 8VC, and Accel among the potential investors. The Fractile team reportedly includes engineers from Graphcore, Nvidia, and Imagination Technologies, and the company is building its own software stack alongside the hardware.
Anthropic has deliberately avoided dependence on any single chip vendor, running Claude on Nvidia GPUs, Amazon's Trainium processors through Project Rainier, and Google's TPUs under a deal announced in October that provided over 1GW of compute capacity. In early April, that expanded to 3.5GW of TPU capacity from 2027 through 2031.
The interest in Fractile coincides with surging demand on Anthropic's existing infrastructure. The company's annualized revenue run rate passed $30 billion in March, up from around $9 billion at the end of 2025, and its inference costs have been a drag on gross margins. Unlike OpenAI and xAI, which are building or expanding their own massive data center footprints, Anthropic has opted to rent capacity from multiple providers and negotiate leverage through diversified chip supply.
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Fractile is one of several inference-focused startups pursuing SRAM-based or near-memory architectures, including Groq and Cerebras. Nvidia struck a $20 billion acquisition deal with Groq in December and subsequently launched its own dedicated inference accelerator, Groq 3 LPX, acknowledging the growing commercial pressure to optimize cost-per-token at scale.
Follow Tom's Hardware on Google News, or add us as a preferred source, to get our latest news, analysis, & reviews in your feeds.
Luke James is a freelance writer and journalist. Although his background is in legal, he has a personal interest in all things tech, especially hardware and microelectronics, and anything regulatory.
-
alan.campbell99 2027, assuming Anthropic doesn't fall over and die if the bubble pops. How will they pay for these on top of all their other commitments alongside their insane cash burn. This ARR that gets thrown around is a have, I believe to date they've made something like 5 billion? They have this apparent surging demand yet still signing up as many customers as they can get their hands on? At least there as a token acknowledgement of their inference costs, neither they nor openAI are profitable here. I do wish some tech reporters would stop blindly accepting details from known liars and con men, maybe start being a bit more critical instead of carrying these guy's water.Reply -
American2021 Reply
It is a private LLC so no financials available at the sec.gov website. Their detailed internal financials remain confidential and unavailable. This fuels a lot of speculation and interesting reporting. That said they did file a Form D which can be accessed in the EDGAR database but there is very limited data there. Presently, there is a lot of speculative reporting around Anthropic PBC with the usual suspects (e.g., Crunchbase, PitchBook, Bloomberg, etc.) that report on private company valuations likely off track to whatever degree they are.alan.campbell99 said:2027, assuming Anthropic doesn't fall over and die if the bubble pops. How will they pay for these on top of all their other commitments alongside their insane cash burn. This ARR that gets thrown around is a have, I believe to date they've made something like 5 billion? They have this apparent surging demand yet still signing up as many customers as they can get their hands on? At least there as a token acknowledgement of their inference costs, neither they nor openAI are profitable here. I do wish some tech reporters would stop blindly accepting details from known liars and con men, maybe start being a bit more critical instead of carrying these guy's water. -
bit_user Reply
Yes, most purpose-built AI chips I've read about seem to do this, including Tenstorrent and Graphcore (defunct, I think). The downside is that it takes potentially lots and lots of chips, in order to use it for inferencing large models.The article said:Fractile is one of several inference-focused startups pursuing SRAM-based or near-memory architectures, including Groq and Cerebras.