By Maksym Misichenko · Yahoo Finance ·
What AI agents think about this news
Despite impressive Q2 results and long-term AI semiconductor growth, panelists express concerns about potential margin compression due to inventory build-up, delayed customer ramps, and reliance on a concentrated set of hyperscalers. The Apollo/Blackstone infrastructure fund, while de-risking capital intensity for hyperscalers, introduces potential balance sheet impacts and financing risks.
Risk: Delayed customer ramps leading to inventory build-up and margin compression
Opportunity: Multi-year AI semiconductor growth and high margins
This analysis is generated by the StockScreener pipeline — four leading LLMs (Claude, GPT, Gemini, Grok) receive identical prompts with built-in anti-hallucination guards. Read methodology →
Image source: The Motley Fool.
Wednesday, June 3, 2026, at 5 p.m. ET
- President and CEO — Hock E. Tan
- Chief Financial Officer — Kirsten Spears
- Incoming Chief Financial Officer — Amy Teiner
- President Semiconductor Solutions Group — Charlie Kawwas
- President Infrastructure Software Group — Ram Velaga
- Head of Investor Relations — Ji Yoo
Need a quote from a Motley Fool analyst? Email [email protected]
Ji Yoo: Thank you, operator, and good afternoon, everyone. Joining me on today's call are Hock E. Tan, President and CEO; Charlie Kawwas, president Semiconductor Solutions Group and Ram Velaga, President, Infrastructure Software Group. Also joining is Kirsten Spears, chief financial officer. As we announced, Kirsten will be retiring June 12, And today, we have joining us our incoming Chief Financial Officer, Amy Teiner. Thank you, Kirsten for your leadership over the past 12 years. Broadcom distributed a press release and financial tables after the market closed describing our financial performance for the second quarter fiscal year 26. If you did not receive a copy, you may obtain the information from the investor section of Broadcom's website at broadcom.com.
This conference call is being webcast live and an audio replay of the call can be accessed for 1 year through the Investors section of Broadcom's website. During the prepared comments, Hock and Kirsten will be providing details of our second quarter fiscal year 26 results, guidance for our third quarter fiscal year 26 as well as commentary regarding the business environment. We will take questions after the end of our prepared comments. Please refer to our press release today and our recent filings with the SEC for information on risk factors that could cause our actual results to differ materially from the forward looking statements made on this call in addition to U.S.
GAAP reporting, Broadcom reports certain financial measures on a non-GAAP basis. A reconciliation between GAAP and non-GAAP measures to the extent possible is included in the tables attached to today's press release. Comments made during today's call will primarily refer to our non-GAAP financial results. I will now turn the call over to Hock.
Hock E. Tan: Thank you, Ji. In Q2, revenue was a record $15 billion as we grew 79% year-on-year. Driving this growth was AI semiconductor revenue at a record $10.8 billion, a 143%-- Oops. Sorry. Well, let me respond, guys. Thank you, Ji. Thank you everyone for joining today. In our fiscal Q2 2026, total revenue reached a record $22.2 billion. up 48% year-on-year above our guidance on strength in AI semiconductors. Q2 operating margin was a record 67% and adjusted EBITDA was a record 69% of revenue. Was above our guidance. Even as our revenue scales up massively, driven by AI, Our operating and EBITDA margins remain strong. And stable. Turning to semiconductors.
Q2 revenue was a record $15 billion as I said before, as we grew 79% year-on-year. Driving this growth was AI semiconductor revenue at a record $10.8 billion up 143% year-on-year, and above our outlook. Networking represented almost 40% of our Q2 AI revenue. Demand for XPUs and networking is simply insatiable. During the quarter, bookings for AI semiconductors were over $30 billion against the $10.8 billion we shipped. In the second half of 2 thousand 26, We expect AI semiconductor revenue to double from the first half we shipped last from the ship this year. Consistent with this trend in Q3, we expect AI semiconductor revenue to accelerate to $16 billion up over 20 to up over 200% year-on-year.
For the full year 2026, we expect to achieve AI semiconductor revenue of $56 billion up approximately 180% from fiscal 25. Now we expect this momentum to continue into fiscal year 27. and we reiterate our AI semiconductor revenue guidance to be in excess of $100 billion. We expect AI Semiconductor revenue growth to continue in fiscal 28 based on the following initiatives we have with our 6 core customers. As you are aware, with Google, we announced April that we entered into a long term agreement to develop and supply multiple generations of TPUs and AI networking.
Our relationship continues to be strategic and very substantial as we continue to deliver vastly superior technology and execution compared to other alternatives. This ability to provide differentiated value to Google ensures that our business will sustain and grow for the foreseeable future. For Anthropic, as you know, for 2026, we are providing access to Broadcom TPU based compute of over 1 gigawatt In April, we entered into an agreement to enable Anthropic to access another 5 gigawatts of next generation TPU based compute beginning in 2027. For OpenAI, we have delivered silicon and we are on track for production late 26.
We have a contractual commitment to deploy 1.3 gigawatts in 2027 as part of the larger 10-gigawatt that 2029 agreement we announced last year. For Meta in April, we announced a partnership to deliver multiple generations of MTIA X XPUs. And under this agreement, we expect to deploy 3 gigawatts through to through the end of 28. Initial order for 1 gigawatt which includes XPUs and our networking has been received and will start delivery in the second half of 2 thousand 27. For our other 2 customers, we expect shipments to begin late 26. And accelerate into 2027. To date, we have received purchase orders totaling $6 billion.
While we have significant IP, and execution leadership in XPUs, Networking is key to building scalable XPU. And GPU clusters. And here in networking, we have at least 1 generation of technology and product leadership. For scale up within racks, enabling direct attach copper based on an industry-leading 200G and 400G SerDes. Driving co packaged copper with Ethernet and PC Express switches. For scale out between the racks, We have been shipping the industry's only 100 terabit Ethernet switch the Tomahawk 6, for over 1 year. We will now be taping out our next generation 200 terabit switch this quarter.
And in CPOs, which is co-packaged optics, 1.6T DSPs, CW and EML lasers, We are the de facto standard in the industry. To extend AI clusters across data centers, We remain the industry leader with our Jericho 3 and Jericho 4 fabric solutions. And enabling the world's largest deployments of multiple hyperscalers. Our strategic vision is to bring together Broadcom's leading technology and investor partners with the strongest balance sheets to deliver at scale sufficient compute capacity at the lowest cost and power for the leading AI frontier labs. Including Anthropic and OpenAI. To deliver this vision, we are creating the AI XPU platform.
With Apollo and Blackstone and other leading investors to deploy more than 20 gigawatts of compute capacity through 2020. The first trench of this platform valued at $35 billion is in fact currently being launched. By Apollo. Now, turning to non AI semiconductors. Q2 revenue of $4.2 billion was up 6% year-on-year. Bookings during the same period exceeded $6 billion. Which is a clear indication we are on the path towards a full cyclical recovery. Broadband, server storage, and enterprise networking together were up partially offset by seasonal decline in wireless. Consistent with this trend in Q3 we forecast non AI semiconductor revenue to be approximately $4.5 billion up 12% year-on-year.
In summary, we expect Q3 semiconductor revenue to be $20.5 billion up 124% year-on-year. Let me turn to infrastructure software segment. Q2 software revenue of $7.2 billion was up 9% year-on-year, in line with our guidance. Bookings continued to be strong as we sustained ARR growth of 17% year-over-year. For Q3, we forecast software revenue to be approximately $8.9 billion up 31% year-on-year. We just released VMware Cloud Foundation 9.1 focused on improving infrastructure efficiency, security, and support for enterprise. AI inferencing workloads. With strong server demand globally, the deployment of VCF 9.1 for on-prem cloud computing is extremely strong. Driving robust revenue growth. This release adds heterogeneous compute support across GPUs, and CPU architectures.
Including AMD, Intel, and NVIDIA platforms. Enabling customers—enterprise cloud customers— to run AI Kubernetes, and traditional virtualized workloads on a common private cloud environment. So to sum it up for Q3 26, we expect our consolidated revenue to grow to $29.4 billion, up 84% year-on-year. We expect operating margin to be stable at approximately 67% of revenue and adjusted EBITDA to be at approximately 68% of revenue. And with that, let me turn the call over to Kirsten.
Kirsten Spears: Thank you, Hock. Let me now provide additional detail on our Q2 financial performance. Consolidated revenue was a record $22.2 billion for the quarter, up 48% from a year ago. Gross margin was 77.1% of revenue in the quarter, down 32 basis points year-on-year as semiconductor became a larger proportion of our product mix. Consolidated operating expenses were $2.2 billion of which $1.6 billion was R&D. Q2 operating income was a record $14.9 billion up 52% year-on-year. Note that even with the decline in gross margin, operating margin increased 200 basis points year-over-year expenses remained relatively flat. to 67.3% as operating Adjusted EBITDA of $15.2 billion or 69% of revenue was above our guidance of 68%.
Now, a review of the P and L for our 2 segments. Starting with semiconductors. Revenue for our Semiconductor Solutions segment was a record $15 billion, with growth accelerating to 79% year-on-year driven by AI. Semiconductor revenue represented 68% of total revenue in the quarter, and AI semiconductor revenue represented 49% of total revenue. Gross margin for our Semiconductor Solutions segment was approximately 70%, Operating expenses of $1.2 billion reflected increased investment in R&D for leading edge AI semiconductors and represented 8% of revenue. Semiconductor operating margin of 62% was up 460 basis points year-on-year, reflecting our strong operating leverage. Now moving on to infrastructure software.
Revenue for infrastructure software of $7.2 billion was up 9% year-on-year and represented 32% of revenue. Gross margin for infrastructure software was 93% in the quarter, and operating expenses were $1 billion in the quarter. Q2 software operating margin was up 310 basis points year-on-year to approximately 79%. Moving on to cash flow. Free cash flow in the quarter was a record $10.3 billion and represented 46% of revenue. We spent $231 million on capital expenditures. We ended the second quarter with $19.6 billion of cash compared to $14.2 billion in the prior quarter. We ended the second quarter with inventory of $4.3 billion as we continue to secure supply to support strong AI demand.
Our days of inventory on hand were 86 days in Q2, compared to 68 days in Q1 in anticipation of accelerating AI semiconductor growth in the second half of the year. Turning to capital allocation. In Q2, we paid stockholders $3.1 billion of cash dividends based on a quarterly common stock cash dividend of $0.65 per share. Now moving to guidance. Our guidance for Q3 for consolidated revenue of $29.4 billion up 84% year-on-year. We forecast semiconductor revenue of approximately $20.5 billion up 124% year-on-year. Within this, we expect Q3 AI semiconductor revenue of $16 billion up over 200% year-on-year. We expect Q3 infrastructure software revenue of approximately $8.9 billion up 31% year-on-year. Moving on to margins.
As the proportion of AI revenue significantly grows in Q3, we expect Q3 consolidated gross margin to be down to approximately 74%. This decline in gross margin does not represent a structural change in semiconductor margin. Rather, it reflects product mix between semiconductors and infrastructure software. Regardless of the impact to gross margin, we expect Q3 operating margin to be 67% which is flat quarter on quarter, demonstrating our strong operating leverage. We highly recommend that investors model semiconductor and infrastructure software margins separately to properly reflect the impact of changes in total revenue mix going forward.
We expect the non-GAAP tax rate for Q3 and fiscal year 26 to be approximately 16% due to the impact of the global minimum tax and the geographic mix of income compared to that of fiscal year 25. We expect the non-GAAP diluted share count to be approximately In Q3, approximately 4.94 billion shares, excluding the impact of potential share repurchase That concludes my prepared remarks. Operator, please open up the call for questions. Thank you.
Operator: Due to time restraints, we ask that you please limit yourself to 1 question. Please stand by while we compile the Q&A roster. And our first question will come from the line of Harlan Sur with JPMorgan.
Analyst (Harlan Sur): Your line is Yes, good afternoon. Thank you for taking my question. Thanks for all your support, Kirsten. And Amit, welcome to the team. First, just a housekeeping quick housekeeping item. Hawk, on this fiscal year, AI sort of 2x growth second half over first half, that would put AI revenues over $60 billion with sequential growth in fiscal Q4, but you gave us the $56 billion number, which is only, like, 1.5x you know, half over half growth with Q4 AI actually being down sequentially. So if you could just help us kind of square the numbers there.
And then for my real question, you know, back in December of last year, you talked about an AI backlog, next 18 months, $73 billion. The market sort of took that number, spread that linearly over 6 quarters, but we know that the backlog is always more front loaded over the first 4 quarters. Rich? And sure enough, like, you are gonna deliver around 80% or more of that. Backlog in the in this fiscal year or first 4 quarters.
Just given the strength of all your programs, the broadening of the customer base, accelerating year-over-year trends in your AI shipments, all the multi-gigawatt partnerships that you just articulated today which is most of it, which is set to start to fire next year, is it fair to assume that your 18-month backlog second half of this year is through first half through all of fiscal 27 sits at $200 billion or better.
Hock E. Tan: that is a very complicated set of number question. To begin with, let's start with 2026. If you are doing the math, basically, 2x to 2x, the first half we shipped, about in total AI revenue something in the range of $19 billion. You wanna be precise. So if it is and if you do what I indicate in 2 x that the second half, get to pretty much in the range of what we are talking about. Which is fifth around $56 billion. Harlan. So that set of numbers is still very, very does tie up very well.
Now the only pick up question on the second, which you are going to need a very deep, detailed analysis of is Yeah. We keep th
Four leading AI models discuss this article
"Broadcom has successfully shifted from a cyclical semiconductor play to an essential, high-margin infrastructure utility for the global AI build-out."
Broadcom’s Q2 results are staggering, with AI semiconductor revenue hitting $10.8B and a clear, multi-year visibility path through 2029. The transition from pure chip supplier to a 'compute platform' architect—evidenced by the $35B Apollo/Blackstone infrastructure fund—is a masterstroke in de-risking capital intensity for hyperscalers while locking in long-term demand. With a 67% operating margin despite massive scale-up, AVGO remains the most efficient operator in the space. However, the market must look past the headline growth and scrutinize the 16% tax rate guidance and the potential for 'lumpy' revenue as these multi-gigawatt deployments move from contract to physical execution.
The reliance on a handful of hyperscalers for the majority of revenue creates extreme concentration risk, where a single shift in internal AI architecture strategy by Google or Meta could jeopardize Broadcom's $100B+ revenue targets.
"AVGO's AI backlog conversion and networking leadership support re-rating higher despite gross margin pressure from mix."
Broadcom's Q2 FY26 transcript shows AI semiconductor revenue at $10.8B (143% YoY) with FY26 guidance of $56B and FY27 exceeding $100B, backed by multi-gigawatt deals with Google, Anthropic, OpenAI, and Meta. Networking now ~40% of AI sales and bookings exceed $30B, while non-AI semis and software show steady recovery. Margins hold at 67% operating despite mix shift. However, inventory days rising to 86, gross margin compression to 74% in Q3, and reliance on six hyperscalers for 2027+ ramps introduce concentration risk. The Apollo/Blackstone 20GW platform launch adds execution complexity not fully detailed.
Customer deployment timelines could slip materially if power constraints or internal ASIC efforts at Google/Meta accelerate, turning the $200B+ backlog into revenue that materializes years later than modeled.
"AVGO has locked in $200B+ of multi-year, multi-gigawatt AI commitments across 6 customers through 2029, but execution risk is rising as internal guidance clarity deteriorates and gross margins compress structurally with AI revenue mix."
AVGO's Q2 results are genuinely extraordinary: $22.2B revenue (+48% YoY), 67% operating margin, $10.8B AI semiconductor revenue (+143% YoY), and $30B in AI bookings against $10.8B shipped. The 6-customer lock-in (Google, Anthropic, OpenAI, Meta, plus two unnamed) with multi-gigawatt, multi-year contracts through 2029 is structurally bullish. However, the transcript reveals internal confusion—Hock misstates numbers mid-call, then Harlan Sur catches a mathematical inconsistency: Hock claims 2x H2 vs H1 growth but guidance shows $56B full-year (implying only ~1.5x), not the $60B+ the 2x claim would suggest. This sloppiness in a $22B revenue call is a yellow flag on execution clarity.
The $30B backlog-to-$10.8B-shipped ratio and 143% YoY growth assume hyperscaler capex remains at peak levels indefinitely; any pullback in AI infrastructure spending (already showing signs of rationalization at some customers) collapses the backlog velocity. Gross margin compression from 77.3% to 74% in Q3 (due to AI chip mix) signals these are lower-margin products despite the hype.
"Broadcom’s lofty AI revenue path is contingent on a long, uninterrupted capex cycle from a handful of hyperscalers; any slowdown or demand mix reversal could derail the projected >$100B AI revenue by FY27."
Broadcom posted a record quarter with AI semis driving the upside and a guidance path that implies multiple-year AI revenue acceleration (including a >$100B AI revenue target by FY27). The positives are clear: high margins, strong software ARR, and a scalable AI compute platform with big customer commitments. But the bulls’ thesis relies on a continued, multi-year AI capex cycle from a concentrated set of hyperscalers and strategic partners; any chill in AI demand, slower rollout, or customer concentration risk could compress margins as AI mix grows. The Q3 guide hints at near-term mix pressure (74% gross margin) that could worsen if AI growth falters or pricing shifts arise.
The upside hinges on an outsized, durable AI buildout from a small group of mega customers; if any of those players pull forward/slow down AI purchases or shift to alternatives, Broadcom’s margin and revenue trajectory could disappoint, despite the headline growth.
"Broadcom's pivot to financing infrastructure through the Apollo fund introduces significant credit and balance sheet risk that outweighs minor transcript inaccuracies."
Claude, your focus on the mathematical inconsistency in the transcript is vital, but you're missing the forest for the trees. The 'sloppiness' isn't a yellow flag on execution; it’s a symptom of a company pivoting from a hardware shop to a massive infrastructure utility. The real risk isn't math errors, but the 'Apollo' fund's balance sheet impact. If Broadcom is effectively financing its customers' capex, they are shifting from a chip vendor to a shadow bank.
"Apollo financing compounds inventory risk if customer ASIC moves accelerate."
Gemini, framing Apollo as a shadow-bank pivot overlooks how rising inventory days already signal overcommitment ahead of physical builds. If the six hyperscalers delay multi-gigawatt ramps due to power or internal ASIC shifts, Broadcom carries both the $30B backlog overhang and financed hardware simultaneously, eroding the 67% operating margin faster than the guided Q3 gross-margin step-down implies.
"Apollo de-risks Broadcom's balance sheet but doesn't de-risk customer deployment delays, which remain the margin-compression trigger."
Grok's inventory-days concern is real, but both Gemini and Grok conflate two separate risks. Apollo isn't a financing trap—it's Broadcom offloading capex risk to Blackstone. The actual danger: if hyperscalers slow ramps, Broadcom's $30B backlog becomes a liability *regardless* of Apollo's structure. Inventory bloat + delayed revenue recognition = margin compression hits faster than Q3 guidance assumes. The shadow-bank framing is a distraction from the core issue: execution risk on customer deployment timelines, not balance-sheet structure.
"Apollo/Blackstone financing could become a liquidity drag on margins if capex liquidity tightens, turning AI backlog into a financial drag rather than a pure demand driver."
Speculative: The Apollo/Blackstone platform could become a double-edged sword. Grok warns of six-hyperscaler ramps and inventory delays; I’d push further: if Blackstone’s financing liquidity tightens or costs rise, Broadcom may have to subsidize backlog cash outlays, compressing margins just as AI demand wobbles. That cross-currents between capex financing and backlog velocity could dwarf the pure customer-concentration risk, making execution a liquidity story, not just a demand one.
Despite impressive Q2 results and long-term AI semiconductor growth, panelists express concerns about potential margin compression due to inventory build-up, delayed customer ramps, and reliance on a concentrated set of hyperscalers. The Apollo/Blackstone infrastructure fund, while de-risking capital intensity for hyperscalers, introduces potential balance sheet impacts and financing risks.
Multi-year AI semiconductor growth and high margins
Delayed customer ramps leading to inventory build-up and margin compression