Etched.ai
Company type | Private |
---|---|
Industry | Semiconductors |
Founded | 2022 |
Founders |
|
Headquarters | , |
Key people |
|
Products | Sohu (transformer ASIC) |
Number of employees | 35 (2024)[note 1] |
Website | www |
Etched.ai Inc. (stylized Etched.ai) is an American semiconductor start-up that is designing Sohu, an ASIC built exclusively for transformer inference in large language models.[2] Founded in 2022 by two Harvard University drop-outs, Gavin Uberti and Chris Zhu, the company raised US$120 million in a Series A round in June 2024 to fabricate its first chips at TSMC.[1] The round was co-led by venture-capital firms Primary Venture Partners and Positive Sum Ventures, and drew angel investors such as Peter Thiel, Stanley Druckenmiller and Kyle Vogt.[3]
History
Uberti began experimenting with compiler optimizations for AI workloads in 2022 and recruited classmate Zhu to pursue a chip start-up.[2] The pair incorporated the company in Silicon Valley and hired Robert Wachen, a former Cypress Semiconductor executive, as chief operating officer.[4]
In March 2023 the start-up closed a US$5.4 million seed round that valued the company at US$34 million.[1]
Technology
Sohu is fabricated on TSMC's 4-nanometre process node and hard-wires the matrix multiplication patterns specific to transformer inference.[2] Because the chip omits hardware needed for other neural-network types, Etched has claimed that an eight-chip Sohu server can generate more than 500,000 tokens per second on Llama-70B, versus roughly 23,000 tokens per second for an eight-GPU Nvidia H100 system.[5] Uberti has asserted that “one Sohu server replaces 160 H100 GPUs,” positioning the device as a lower-cost, lower-power competitor to Nvidia's Blackwell architecture.[4]
Funding
Date | Round | Amount (US$) | Lead investors |
---|---|---|---|
March 2023 | Seed | 5.4 million | Various angels |
June 2024 | Series A | 120 million | Primary Venture Partners, Positive Sum Ventures |
Other participants in the Series A included Peter Thiel, GitHub CEO Thomas Dohmke, Balaji Srinivasan and Kyle Vogt.[6]
Reception
Trade press and analysts describe Etched as part of a “second wave” of AI accelerator companies that aim to undercut Nvidia's general-purpose GPUs.[4] CNBC characterised the firm's focus on transformers as “the biggest bet in AI,” noting that its survival depends on the continued dominance of that architecture.[3]
See also
Notes
References
- ^ a b c Cherney, Max A. (June 25, 2024). "AI startup Etched raises $120 million to develop specialized chip". Reuters. Retrieved August 8, 2025.
- ^ a b c Wiggers, Kyle (June 25, 2024). "Etched is building an AI chip that only runs one type of model". TechCrunch. Retrieved August 8, 2025.
- ^ a b "Etched raises $120 million to build chip to take on Nvidia in AI". CNBC. June 25, 2024. Retrieved August 8, 2025.
- ^ a b c Wheatley, Mike (June 25, 2024). "Transformer-model chipmaker Etched.ai raises $120M to challenge Nvidia's market dominance". SiliconANGLE. Retrieved August 8, 2025.
- ^ Trueman, Charlotte (June 26, 2024). "AI chip startup Etched.ai raises $120 million to take on Nvidia". DataCenterDynamics. Retrieved August 8, 2025.
- ^ Zaveri, Paayal (June 25, 2024). "AI chip startup Etched raises $120 million to expand supply". Bloomberg Law. Retrieved August 8, 2025.