Thursday, January 15th 2026

Samsung Foundry Supposedly Achieves 50% Yields with 2 nm GAA Node Process

Late last year, conflicting insider reports provided jumbled details of Samsung's cutting-edge 2 nm GAA node process (SF2). Around that period, the South Korean megacorp's semiconductor business had initiated "mass production" of proprietary next-gen Exynos 2600 mobile processors. Earlier today, a ZDNet news article claims that yields of Samsung's first-generation 2 nm wafer product have been recorded hitting a "relatively stable" 50% milestone. This more recent achievement is puzzling, given that other inside sources disclosed a similar level being reached last September. Ideally, closer to 70% yield rates are preferred for mass manufacturing of finalized chip designs. Throughout 2025, insider reports suggested a not so smooth development of SF2—company leadership was determined to get this technology over the finishing line. Industry observers think that the alleged failure of Samsung Foundry's 3 nm line had caused potentially returning clients to stick with TSMC.

The upcoming launch of Exynos 2600 chip will be a crucial "proof of concept" moment for Samsung—with the opportunity to attract VIP customers away from a main rival's best 2 nm and 3 nm offerings. The ZDNet report mentions a second-gen 2 nm GAA option (SF2P). This refinement could be the result of "additional growth engines," and inside track info posits that guidelines have been sent to design solution partners. When compared to the first iteration, SF2P reportedly does better with: "12% improved performance, 25% improved power efficiency, and an 8% smaller footprint." One anonymous source divulged that SF2P's basic process design kit (PDK) was completed mid-way through last year. ZDNet has linked this second-gen node process to a mysterious "Exynos 2700" SoC.
Sources: ZDNet SK, Wccftech
Add your own comment

4 Comments on Samsung Foundry Supposedly Achieves 50% Yields with 2 nm GAA Node Process

#1
Panther_Seraphin
50% isnt bad but its still horrendous from a economically viable perspective!

Imagine a 300mm 2nm wafer full of 5090 dies and only ~50% are viable............

TSMCs wafers were supposedly ~18k a wafer, with 71 dies total on a wafer and only 50% viable. Each viable die is $500 in materials alone let alone the R+D cost etc involved
Posted on Reply
#2
john_
With Intel having the necessary support to become an alternative to TSMC, Samsung's time is nearing to an end. Either they make it work, or they will have a real problem. I don't think they can keep investing in "the next node" any more. The costs are great and if they give more time to Intel, those potential customers will use Intel as a second source.
Posted on Reply
#3
kondamin
Panther_Seraphin50% isnt bad but its still horrendous from a economically viable perspective!

Imagine a 300mm 2nm wafer full of 5090 dies and only ~50% are viable............

TSMCs wafers were supposedly ~18k a wafer, with 71 dies total on a wafer and only 50% viable. Each viable die is $500 in materials alone let alone the R+D cost etc involved
I think most of us would be happy with 5070ti dies paired with 24GB of gddr.
john_With Intel having the necessary support to become an alternative to TSMC, Samsung's time is nearing to an end. Either they make it work, or they will have a real problem. I don't think they can keep investing in "the next node" any more. The costs are great and if they give more time to Intel, those potential customers will use Intel as a second source.
they might slowdown a bit, but they are in the foundry business for memory, nand, sensors probably more things.
They need to keep he expertise of high end nodes and the company is a colossus so smaller scale is probably well in the budget
Posted on Reply
#4
Atomofvoid
They did it. They achieved the end of transistor size reducing. With the 2 nanometer size, there is no way to go down any further from now on.
Posted on Reply
Nov 19th, 2026 04:09 PST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts