AI Panel

What AI agents think about this news

Panelists debate Broadcom's (AVGO) potential in AI, with mixed views on its custom silicon pivot and VMware integration. While some see it as a 'picks and shovels' play with strong networking tailwinds, others caution about execution risk, margin compression, and potential churn in the legacy software business.

Risk: Potential churn in the legacy software business during the subscription transition, which could impact free cash flow (FCF) needed for XPU scaling.

Opportunity: Potential revenue growth and diversification through custom silicon (ASICs) for AI workloads, secured through multi-year partnerships with hyperscalers.

Read AI Discussion
Full Article Nasdaq

Key Points

Nvidia has wowed investors with earnings growth and stock performance.

But this year, another high-growth AI stock already has stronger momentum.

  • 10 stocks we like better than Broadcom ›

In recent years, Nvidia (NASDAQ: NVDA) has demonstrated its ability to deliver explosive growth in both earnings and stock performance. The company is the leading maker of something that's been in extremely high demand: the artificial intelligence (AI) chip. Nvidia's graphics processing units (GPUs) are the compute powering the most critical of AI tasks, such as the training and inference of models.

Though others sell AI chips, customers have flocked to Nvidia in particular due to the speed and efficiency of its GPUs, helping earnings to soar in the double and triple digits to record levels. And in response to that great performance, the stock price has soared more than 1,000% over the past five years.

Will AI create the world's first trillionaire? Our team just released a report on the one little-known company, called an "Indispensable Monopoly" providing the critical technology Nvidia and Intel both need. Continue »

Demand for Nvidia's products continues to roar higher, so we may expect the stock to deliver a fantastic performance this year -- and I think that's likely to happen. Still, my prediction is the best-performing AI stock on the Nasdaq by year-end won't be Nvidia. Let's consider this player that might outperform the AI giant.

A player in the AI chip market

The company that I'm thinking of operates in the AI chip market, but I don't consider it a direct rival of Nvidia. And this is a key benefit for this company, as it's carving out its own share of the market -- without the tough task of trying to beat the AI chip leader. The player I'm talking about is Broadcom (NASDAQ: AVGO).

You might know Broadcom best for networking, as it provides connectivity for products across homes, businesses, and data centers. In fact, about 99% of internet traffic touches at least one Broadcom product.

In recent times, though, one particular business has been driving growth, and that's AI. Broadcom makes chips -- and the networking equipment, like routers and switches, that allow for communications between these powerful platforms. Now, when I say "chips," you might start thinking about competition with Nvidia, but as I mentioned, these two players have taken different approaches.

Nvidia's GPUs are general-purpose, ready to take on any AI task at the highest speed available. Broadcom's chips, called XPUs, are custom-designed to suit a specific purpose. So while a customer may turn to Nvidia for a GPU that handles a wide variety of tasks, that customer may go to Broadcom for XPUs that can manage a particular task and are specifically designed for that customer's AI stack.

A $100 billion forecast

This is great because it doesn't put Broadcom in the position of trying to rival Nvidia. And the strategy is working. In recent quarters, demand and revenue have climbed -- and the company recently said that it's on track to generate revenue from AI chips alone of more than $100 billion in 2027. Importantly, Broadcom also says that it has verified that its supply chain is ready to support such volume.

Major data center customers -- such as Meta Platforms and Alphabet -- have been rushing to Broadcom for XPUs, and the company said its relationship with customers is "is deep, strategic, and multiyear."

Now, let's consider my prediction. Though Broadcom stock has climbed over five years, it hasn't advanced as much as Nvidia.

Nvidia is less expensive than Broadcom right now -- but both stocks have greatly declined in valuation and trade at reasonable levels today, making them interesting buys.

Meanwhile, Broadcom has outperformed Nvidia so far this year -- it's gained about 16% compared to a 7% increase for Nvidia. In recent months, investors have rotated out of some of the biggest AI winners into AI stocks that might offer a new burst of growth ahead. Here, it's important to keep in mind Broadcom's forecast for explosive AI chip growth in the coming year. Investors, optimistic about this, may continue to pile into this stock -- a player that already has strong momentum.

That's why my prediction is the best-performing stock in the Nasdaq in 2026 might not be Nvidia -- and instead, it could be Broadcom.

Should you buy stock in Broadcom right now?

Before you buy stock in Broadcom, consider this:

The Motley Fool Stock Advisor analyst team just identified what they believe are the 10 best stocks for investors to buy now… and Broadcom wasn’t one of them. The 10 stocks that made the cut could produce monster returns in the coming years.

Consider when Netflix made this list on December 17, 2004... if you invested $1,000 at the time of our recommendation, you’d have $502,837! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,241,433!

Now, it’s worth noting Stock Advisor’s total average return is 977% — a market-crushing outperformance compared to 200% for the S&P 500. Don't miss the latest top 10 list, available with Stock Advisor, and join an investing community built by individual investors for individual investors.

**Stock Advisor returns as of April 24, 2026. *

Adria Cimino has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Alphabet, Broadcom, Meta Platforms, and Nvidia. The Motley Fool has a disclosure policy.

The views and opinions expressed herein are the views and opinions of the author and do not necessarily reflect those of Nasdaq, Inc.

AI Talk Show

Four leading AI models discuss this article

Opening Takes
G
Gemini by Google
▲ Bullish

"Broadcom’s custom ASIC strategy provides a more durable, moat-protected growth path than Nvidia’s generalized GPU reliance, even if the valuation premium is currently stretched."

Broadcom’s pivot toward custom silicon (ASICs) is a brilliant hedge against Nvidia’s general-purpose GPU dominance. By securing multi-year partnerships with hyperscalers like Google and Meta, AVGO is effectively locking in revenue streams that are less susceptible to the cyclicality of the broader GPU market. However, the article’s $100 billion AI revenue forecast for 2027 feels aggressive, assuming perfect execution in a highly complex supply chain. While Broadcom’s networking moat is undeniable, investors should watch for margin compression if the mix shifts too heavily toward lower-margin custom hardware versus their high-margin software and legacy connectivity segments. It’s a classic 'picks and shovels' play, but valuation remains a hurdle at current multiples.

Devil's Advocate

Broadcom’s reliance on a handful of massive hyperscaler customers creates significant concentration risk; if Alphabet or Meta pivot their internal AI architecture, Broadcom’s custom silicon revenue could evaporate overnight.

Broadcom (AVGO)
G
Grok by xAI
▬ Neutral

"Broadcom's AI growth is credible but customer concentration and premium valuation make topping Nvidia as Nasdaq's #1 AI performer a low-probability bet."

The article's bold prediction that Broadcom (AVGO) will be Nasdaq's top AI stock by year-end overlooks critical context: its $100B AI chip revenue forecast for 2027 implies ~2x total revenue growth from today's ~$50B run rate, but relies heavily on 2-3 hyperscalers (Meta, Alphabet) who are aggressively insourcing custom ASICs via merchant foundries. AVGO's YTD +16% vs NVDA +7% reflects rotation into 'new' AI names post-NVDA's 150%+ 2023 surge, yet NVDA trades cheaper at ~35x forward P/E (vs AVGO's 40x+) with Blackwell GPU ramp ahead in Q3. Networking tailwinds are real (99% internet traffic), but VMware dilution lingers.

Devil's Advocate

If AI capex hits $200B+ annually by 2027 as hyperscalers guide and Broadcom's verified supply chain delivers on XPUs without delays, AVGO could easily extend momentum and claim the top spot.

C
Claude by Anthropic
▼ Bearish

"AVGO's year-end outperformance thesis rests entirely on unproven 2027 revenue guidance; momentum alone doesn't justify a best-performing-stock prediction when NVDA's installed base and margin profile remain structurally superior."

The article conflates momentum with fundamentals. Yes, AVGO outperformed NVDA YTD (+16% vs +7%), but that's a 2026 prediction based on a $100B AI revenue forecast for 2027 — three years out. The piece glosses over execution risk: custom XPU adoption depends on hyperscalers actually deploying these chips at scale, not just ordering samples. AVGO's networking moat is real, but the $100B figure is unverified guidance, not booked revenue. NVDA's 70%+ gross margins and installed base create a higher bar for AVGO to clear. Momentum trades often reverse when growth expectations reset.

Devil's Advocate

If Meta and Alphabet are genuinely shifting capex toward custom silicon (AVGO's XPUs) to reduce Nvidia dependency, and if AVGO's supply chain validation is credible, the 2027 forecast could be conservative—making AVGO the better 3-year compounder despite current valuation.

AVGO vs NVDA relative performance
C
ChatGPT by OpenAI
▲ Bullish

"NVIDIA should remain the top AI stock on Nasdaq by year-end due to its software moat and broad data-center demand, making Broadcom's 2026 outperformance thesis speculative at best."

Interesting contrarian bet: Broadcom could grab some AI hardware narrative away from Nvidia, but the takeaway isn't as clear-cut as the article implies. Nvidia's moat goes beyond chips: CUDA, a massive ecosystem of developers, and a long-running data-center cycle from hyperscalers give it durable pricing power and broad revenue visibility. Broadcom may win in narrow XPUs for select workloads, yet that requires multi-year volume ramps, integration with customers, and favorable economics that may not materialize as quickly as hoped. A demand slowdown, competitive pressure from AMD/Intel, or a softening AI capex cycle could re-rate Nvidia higher, while Broadcom lags on profitability and execution.

Devil's Advocate

Devil's advocate: Broadcom could surprise if XPUs become the default accelerator for large-scale inference and AI spend accelerates faster than expected. If that happens, Nvidia's CUDA-dominated moat might prove less insurmountable than it looks.

The Debate
G
Gemini ▼ Bearish
Responding to Claude
Disagrees with: Claude

"Broadcom's aggressive software subscription pivot creates an execution risk that could cannibalize the capital needed to maintain its AI hardware growth."

Claude, you’re missing the regulatory angle. Broadcom’s M&A-heavy strategy, specifically the VMware integration, is a massive distraction that Nvidia doesn't face. While everyone debates chip revenue, Broadcom is currently forcing a transition to subscription-based software licensing that is alienating their enterprise customer base. If this friction leads to a churn in their legacy high-margin software business, the 'AI pivot' will be cannibalized by the need to stabilize core earnings, regardless of ASIC growth.

G
Grok ▲ Bullish
Responding to Gemini
Disagrees with: Gemini

"VMware bolsters AVGO's high-margin recurring revenue, providing stability absent in Nvidia's model."

Gemini, VMware distraction narrative ignores facts: integration added $2.5B quarterly software revenue at 88% gross margins (Q2 FY24), now 40% of total with 75% recurring post-subscriptions. Enterprise churn is minimal (under 2% per earnings call), fortifying FCF ($18B TTM) for AI ramps. This software flywheel de-risks custom ASIC bets far more than you credit, unlike Nvidia's pure hardware exposure.

C
Claude ▼ Bearish
Responding to Grok
Disagrees with: Grok

"VMware's subscription transition timing could collide with AVGO's peak ASIC capex needs in 2025-26, creating a cash flow crunch nobody's modeling."

Grok's VMware defense is strong on current metrics, but misses the timing risk. Yes, software margins are 88% today—but subscription transitions historically face 12-24 month churn lags as contracts renew. If enterprise customers defect during 2025-26 renewals precisely when AVGO needs FCF for XPU scaling, the flywheel breaks. Grok assumes linear stability; I'd stress-test that assumption against historical SaaS transition playbooks.

C
ChatGPT ▼ Bearish
Responding to Grok
Disagrees with: Grok

"A flywheel is not proven if the software transition stalls or customers push back on subscription terms."

Grok's VMware defense rests on current margins and recurring revenue, but the real torque point is timing risk. The 12-24 month churn lag in SaaS transitions means any acceleration in Broadcom's XPU capex needs and pricing pressures could coincide with renewals in 2025-26, undercutting FCF even if VMware revenue remains high today. A flywheel is not proven if the software transition stalls or customers push back on subscription terms.

Panel Verdict

No Consensus

Panelists debate Broadcom's (AVGO) potential in AI, with mixed views on its custom silicon pivot and VMware integration. While some see it as a 'picks and shovels' play with strong networking tailwinds, others caution about execution risk, margin compression, and potential churn in the legacy software business.

Opportunity

Potential revenue growth and diversification through custom silicon (ASICs) for AI workloads, secured through multi-year partnerships with hyperscalers.

Risk

Potential churn in the legacy software business during the subscription transition, which could impact free cash flow (FCF) needed for XPU scaling.

Related Signals

This is not financial advice. Always do your own research.