Intel details early development lead of 14A process and Nvidia collaboration at TIMT Conference
Amanda Liang, Taipei; Jingyue Hsiao, DIGITIMES Asia
Thursday 20 November 2025
At the 2025 RBC Capital Markets Global Technology, Internet, Media and Telecommunications (TIMT) Conference on November 18, Intel vice president John Pitzer outlined significant progress in the company's next-generation 14A process node. Highlighting...
Copilot:
At the RBC TIMT Conference on November 18, 2025, Intel VP John Pitzer highlighted that the 14A process node is being co-designed with external customers from the outset, making it more suitable for foundry clients and enabling earlier, higher-quality feedback.
Here’s a breakdown of the key points he emphasized:
14A Node Highlights from John Pitzer
- Customer co-design from day one: Unlike previous nodes, Intel is collaborating with external customers during the definitional phase of 14A. This means:
- The node is tailored to foundry customer needs, not just internal Intel products.
- Intel is receiving early and actionable feedback, improving design alignment and reducing risk.
- Shift in capacity strategy:
- Intel is not pre-building massive capacity like it did with 18A.
- Instead, it’s taking a demand-driven approach, scaling only when customer interest is confirmed.
- Pitzer noted this is a departure from the “build it and they will come” mindset that led to $50B in underutilized assets.
- Proof point timeline:
- Hard design choices for 14A will be made in late 2026 to early 2027.
- Intel expects to gauge success trajectory well before that, thanks to current customer engagement.
- “All-in” on 14A development:
- Despite the cautious capacity stance, Intel is fully committed to 14A as a turning point for its foundry business.
Strategic Implications
- Foundry-first mindset: 14A is Intel’s first node built with external customers as primary stakeholders.
- Competitive positioning: This aligns with Intel’s IDM 2.0 strategy and its push to compete with TSMC and Samsung in advanced foundry services.
- Risk mitigation: By avoiding premature capex, Intel aims to prevent the overspending seen in prior nodes.
Let me know if you want to compare 14A’s expected specs vs TSMC’s N2 or track which customers are likely co-designing with Intel.
Cited by Copilot:
Intel Co-Designs 14A Node With Customers, Says "All-In" on Development | TechPowerUp
by AleksandarK Sep 10th, 2025 00:12 Discuss (27 Comments)
At Goldman Sachs technology conference, Intel's presentation spanned multiple Q&A sessions, where the company talked about its upcoming products. On the topic of 14A node, which will be a turning point for Intel Foundry, John Pitzer, Intel's Corporate Vice President of Corporate Planning & Investor Relations, gave a clear message. He stated that "we're just not going to add capacity until we see demand and the need for it. And I think that, that's a shift from how we've been operating in the prior 3-plus years where we did have a little bit of a strategy as if we build it, they might come. And quite frankly, I think the most tangible sort of example of the overspending is over the last 3 or 4 years, our assets under construction went from $20 billion to $50 billion."
However, this doesn't mean that Intel 14A is not getting capacity. Quite the opposite, the company reassures "We are all-in on 14A development." This simply confirms Intel's prior plans to keep 14A capacity lower initially, which is an opposite tactic where the 18A buildout saw massive initial capacity buildup, with little external customer interest. Finally, Pitzer added remarks on co-designing the 14A node with partners and customers: "The big difference on Intel 14A is right in the definitional phase, we are actively engaged with external customers to define the node. And we're also working with Intel products. But quite frankly, what that really means is 14A from the get-go is more suitable for external foundry customers. It also means we're getting earlier, more and better feedback from those external customers. We've talked about sort of some of the hard design choices for 14A that our customers will need to make probably happening in the second half of '26 going into the first half of '27 as far as proof points. But given the interaction we're having today, we'll have a good sense of the trajectory of our success probably well before that." |
