Meta unveils four new chips, the MTIA 300, MTIA 400, MTIA 450, and MTIA 500, set to launch by the end of 2027; the MTIA 300 is in production for content ranking
Meta Platforms Inc. plans to deploy four new generations of its in-house artificial intelligence chips by the end of 2027 …
Bloomberg
Related Coverage
- Meta rolls out in-house AI chips weeks after massive Nvidia, AMD deals CNBC
- Meta unveils plans for batch of in-house AI chips Reuters
- Meta's Race to Scale AI Chips for Billions: Four Chips in Two Years Meta
- Meta Developed 4 New Chips to Power Its AI and Recommendation Systems Wired · Lauren Goode
- Expanding Meta's Custom Silicon to Power Our AI Workloads Meta Newsroom
- Meta doubles down on custom inference chips after reportedly scrapping training chip Sherwood News · Rani Molla
- Meta unveils plans for batch of in-house AI chips Reuters
- Meta unveils next four generations of its MTIA chip DatacenterDynamics · Charlotte Trueman
- Meta unveils new in-house chips to support AI workloads Proactive · Emily Jarvie
- Meta prepares 4 fresh custom AI chips Mobile World Live · Mike Robuck
- Meta's Race to Scale AI Chips for Billions: Four Chips in Two Years — Today, we shared Meta's recent progress and our 2026-2027 roadmap to deliver four AI chip generations in two years. … CQ Tang
- Today, we published a blog post on our MTIA chip program — we're delivering four new generations of custom silicon in just two years, roughly one every six months. … Yee Jiun
- Our MTIA silicon remains central to our AI infrastructure strategy, with four new generations of MTIA chips forthcoming in the next two years to support ranking and recommendations on our apps, along with Gen AI workloads https://about.fb.com/... @metanewsroom
- Will New Custom AI Chips Propel Meta Platforms to $750? 7 Wall St. · David Moadel
- Meta Platforms (META) Announces New AI Chips: New Nvidia Competition? Watcher Guru · Jaxon Gaines
- Today we published a deep dive into Meta's custom AI silicon strategy: four MTIA chips shipped in two years, powering AI experiences for billions of people. … Jonas Olsson
- We have been pretty low-key about our internal silicon development, but decided we needed to get the word out on how things are progressing. … Dan Rabinovitsj
- Meta Announces Four New Custom-Built Chips for Internal Use Wall Street Journal · Meghan Bobrowsky
- Meta further diversifies beyond Nvidia as it unveils four custom AI chips MarketWatch · Britney Nguyen
- Meta's AI chip family is growing. The Verge · Emma Roth
- Meta ‘Sprays Out’ Four MTIA AI Chips in Two Years, Just When Everyone Thought the Custom Chip Efforts Were Dead Wccftech · Muhammad Zuhair
- Meta launches new set of AI chips, but its approach is the big lesson Constellation Research · Larry Dignan
- Meta Packs Gobs of HBM Into Homegrown AI Accelerators HPCwire · Alex Woodie
- Meta Will Deploy Four New In-House Chips to Handle AI Workloads Bloomberg
- Excited to share a bit about some of the AI accelerator work we've been building at Meta! — Custom silicon is critical to scaling next-generation AI systems. … Warner Tsang
Discussion
-
@laurengoode
Lauren Goode
on x
Meta is developing four new chips, part of its MTIA family of AI accelerators, and while they're still going to be used for ranking and recommendations within Meta apps, Meta says it has its eyes set on—you guessed it—inference https://www.wired.com/...
-
@theaustinlyons
Austin Lyons
on x
Huge silicon roadmap announcement from $META. MTIA 300, 400, 450, 500. All optimized for inference. MTIA 300 for recommendations (money printer). MTIA 450, 500 for GenAI inference. Meta and Google have the cleanest ROIC story in custom silicon IMO. MTIA team made good [image]
-
@rihardjarc
Rihard Jarc
on x
$META just dropped their custom ASIC MTIA roadmap (MTIA 300, 400, 450, and 500) One thing that clearly stands out, there is a lot of HBM in that roadmap. The number of different companies bidding for HBM capacity now means the 3 HBM providers have even more negotiating power. I […
-
@aiatmeta
@aiatmeta
on x
Custom silicon is critical to scaling next-gen AI. We're detailing the evolution of the Meta Training and Inference Accelerator (MTIA), our homegrown silicon family designed to power the next era of AI experiences. Traditional chip cycles span years, but model architectures [imag…
-
@stocksavvyshay
Shay Boloor
on x
$META plans to deploy four new generations of MTIA chips over the next two years showing it sees custom silicon as critical for scaling ranking, recommendations & GenAI workloads more efficiently. What stands out is that Meta is building for both ad-driven ranking & GenAI [image]
-
@danielnewmanuv
Daniel Newman
on x
Remembering back to last week when people said $META was canceling its AI chip program. Glad some of us kept it real. 😬🙃
-
@metanewsroom
@metanewsroom
on x
Our MTIA silicon remains central to our AI infrastructure strategy, with four new generations of MTIA chips forthcoming in the next two years to support ranking and recommendations on our apps, along with Gen AI workloads https://about.fb.com/...
-
@laurengoode
Lauren Goode
on x
The most noteworthy thing about these chips might be the cadence with which Meta claims it's developing and shipping them. Co says models are advancing so fast that traditional chip production cycles won't cut it. It's giving chip engineers on adderall https://www.wired.com/...