PodcastChips

Fractile, valued at $7 billion, says its product chip goes to the factory in a few months

Founder Walter Goodwin told the 20VC podcast that test chips are back and trial runs continue, with first systems promised for next year. He said most of the $720 million round is for locking up parts years ahead, from corners of the supply chain his rivals have left.

20VC with Harry StebbingsNov 14, 2026

Taking on NVIDIA: Fractile CEO on the Future of Chips

  • Walter GoodwinFounder and CEO, Fractile
  • Harry StebbingsHost, 20VC

Listen from 27:53

Vincent JiangVincent Jiangfour-minute read
Share
A gloved technician lifts a reflective semiconductor wafer out of processing equipment inside a cleanroom
1 / 6Slide 1 of 6
A wafer comes out of processing equipment at a fabrication plant. Fractile says its own product design has not yet been taped out; founder Walter Goodwin puts that step a few months away.

Test chips are back, and the product design has not been sent

Walter Goodwin, founder and chief executive of Fractile, a British startup that designs chips for running AI models, gave the timing in an interview on the 20VC podcast published November 14 1. Three days earlier Fractile had announced a $720 million funding round that values it at about $7 billion 24.

Host Harry Stebbings put to him another founder's complaint that the chip industry has "a lot of marketing fluff, but there's not much actually in production." Goodwin answered: "Yes, Fractile has silicon that's gone through the foundries, has come back to us. Yes, we're running further trial runs, and we'll be doing sort of full product tape-outs in a few months" 1.

A tape-out is the day a finished chip design is sent to the factory, called a foundry, which builds the stencils used to print it. After that the design cannot be corrected, Goodwin said, so a bug in the file is built into the chip 1.

The schedule leaves little slack in 2027

Goodwin wrote on LinkedIn that the new money will let Fractile "ship [its] first chips and systems next year" 2. In August, Bloomberg reported that Anthropic$350B — Anthropic, private, latest valuation $350B, the maker of the Claude models, had reached an initial agreement to buy roughly $250 million of Fractile chips, and that they would not be ready for use until 2027 5.

By Goodwin's own account, a tape-out is followed by months of waiting for chips to return from the foundry, then by getting software to run on one chip, then on a whole rack of them 1. Fractile's internal finish line is what it calls task zero: "the day that a particular reference workload runs on an entire rack of Fractile chips" 1.

A design sent early next year would have to come back, pass testing and fill racks before the year ends for the shipping target to hold.

Fractile says it avoids the parts its rivals queue for

Goodwin said many custom AI chips, including Google's TPU, Meta's+2.23% — Meta, up 2.23 percent today MTIA and OpenAI's$1.18T — OpenAI, private, latest valuation $1.18T Jalapeno, "are rumored to be using Broadcom−6.53% — Broadcom, down 6.53 percent today" as their back-end partner, the company that does the final physical design and deals with the foundry 1. They also use similar manufacturing lines at TSMC−2.68% — TSMC, down 2.68 percent today, the Taiwanese foundry, and the same high-bandwidth memory, or HBM, which he said is short for years ahead 1.

He recalled Broadcom executive Charlie Kawwas showing a model of its next platform at a conference this summer and saying it would be in production "with six major customers in 2028" 1.

Fractile has "always had that in-house," Goodwin said 1, a point its investor Lightspeed also makes 3. Its design stacks ordinary memory, called DRAM, directly on top of the processor instead of placing HBM beside it 3. Goodwin said that lets it use "a different process node, maybe a slightly different DRAM node or DRAM generation" from the newest HBM, and "build gigawatts of capacity sort of down the back of the sofa" with supply that other chip platforms "have already moved away from" 1.

Memory, not arithmetic, sets how fast a model answers

The design follows from a gap Goodwin put numbers on. Over the last 25 years, he said, the calculating power of these chips has grown "about a million fold," while the rate at which data moves between memory and processor has grown "about 40 fold" 1.

Each word a model writes requires loading the model's weights from memory, so that slower link caps the speed 13. Chips that hold memory on the processor itself, the approach of Groq$3.5B — Groq, private, latest valuation $3.5B and Cerebras, are fast but hold too little, he argued: "You cannot solve LLM inference with these SRAM-based chips. There isn't enough capacity" 1.

Groq is reported to be moving the same way: ZDNet Korea said in October that its next chip will stack DRAM in place of SRAM 7. Goodwin sells a competing design, and Fractile has not shipped a product.

Most of the $720 million is for supply, not the first chip

Asked what the round changes, Goodwin said the cost of getting a first chip and first systems out has been "a kind of fixed cost for the last few years. And in some sense, that's not what most of this capital is used for" 1. He said it pays for "the placing of long-term agreements over certain components that we need to have years into the future," and for work on later chip generations, networking and Fractile's own AI research 1.

He also said Fractile was joined "just a few weeks ago" by Dan Rabinovitsj from Meta to run its systems work, from the chip up to racks, networking and data-center integration 1. Rabinovitsj was Meta's vice president for hardware and AI systems infrastructure engineering in October 2025 6.

Three markers: the tape-out, task zero and the Anthropic order

The first marker is the tape-out itself, which Goodwin placed a few months out 1. The second is task zero, a full rack running a real workload 1. The third is whether Anthropic's reported $250 million commitment becomes a delivery in 2027 5.

Get Chips by email, free

How AI demand is reshaping chipmakers, memory and the fabs behind them. In our daily email, every weekday.

Loading META

Reader comments

0 comments

    Chips

    MaxLinear launches a power chip to save up to half a watt per AI optical module, its answer to Marvell

    The chip is genuine engineering on a thin revenue line: it saves up to half a watt per module, and its job is to help sell MaxLinear's pricier Rushmore DSP into the same socket, the company's first product answer to Marvell's $115 billion Lumentum deal. Samples in February 2027 are the first date the strategy can show up in hardware.

    Chips

    Samsung Electro-Mechanics is 62% off its June peak even as capacitor waits hit 61 weeks

    Korea's press ties the slide to fears of tighter US data-center rules after the midterm elections, but the order book runs the other way: 61-week waits for its capacitors and Nvidia money behind its new substrate lines. The January restock date, and whether about 50 long-term supply contracts hold, will show which side is right.

    Chips

    Bessent gives Nvidia's board 10 days to answer whether suspect China sales inflated its earnings

    Treasury Secretary Scott Bessent has given Nvidia's board 10 days to answer whether suspect China sales inflated its earnings, two days before the first results since Jensen Huang resigned. What moves the stock on Tuesday is the Singapore-billed revenue Nvidia no longer breaks out, presented by interim CEO Colette Kress, who signed the deals under investigation as CFO.

    Chips

    Nvidia director Mark Stevens sold $946 million of stock with no trading plan before the Huang scandal

    He sold near $220 in September; the stock trades near $163, the dip buyers in between are carrying the difference, and Nvidia's first report under interim CEO Colette Kress lands Nov. 17.

    Chips

    Jim Cramer's CNBC club will sell Intel and buy AMD as Intel guides $15-16 billion, below $17 billion expected

    The call came a day after Mercury Research put Intel's desktop CPU share at 70.1%, a gain the research firm says may only be Intel refilling supply in a shrinking PC market. The money is moving to the server CPUs that run AI agents, and AMD is guided to outsell Intel this quarter for the first time.

    Chips

    Nvidia opens its first CEO search in 33 years with Jensen Huang keeping a $132 billion stake

    The board that accepted Jensen Huang's resignation on November 11 handed Nvidia to a finance chief who has never run a profit-and-loss, while the founder's family holds posts across marketing, robotics and AI infrastructure. Tuesday's earnings and a February selling window will price how long the vacuum lasts.

    Subscribe to TheInference for free