Meta is advancing custom MTIA silicon, planning to deploy MTIA 450 (Arke) in H1 2027 and MTIA 500 (Astrid) by end-2027. These target efficient inference workloads with better performance-per-watt and cost than Nvidia systems. Meta partnered with Broadcom and TSMC.
Meta plans to deploy MTIA 450 in early 2027 and MTIA 500 during that year, aiming to lower the cost of running AI. Its expanded Broadcom partnership starts with a commitment exceeding 1 gigawatt. The chips are part of a mixed hardware strategy, and Meta says changing AI workloads can complicate designs years in development.
$META plans to deploy its new in house Arke chips in H1 2027 followed by next generation Astrid chips by year end. Meta says the chips will “save money and energy” as it builds more custom compute alongside its growing AI infrastructure.
The real $META rerating starts when Muse becomes the layer consumers use before they ever open apps like $AMZN, $UBER or $DASH Once the agent controls what gets searched, compared and ultimately bought then Meta starts owning the demand funnel itself and the business looks MUCH…
Meta plans to deploy two new generations of custom AI chips in 2027 as it tries to reduce the cost of running models across its services. Its roadmap, published March 11, schedules MTIA 450 for mass deployment in early 2027 and MTIA 500 during the same year.
Both prioritize inference, the work a trained model does when it responds to a request. Meta says designing around that workload can be more economical than using chips built primarily for large-scale model training. The goal is to make repeated AI use cheaper at the company's scale; the roadmap does not establish a guaranteed saving for each request.
The custom hardware also depends on outside partners. Meta's expanded agreement with Broadcom covers chip design, advanced packaging and networking. In its April 14 announcement, Broadcom said the initial commitment exceeds 1 gigawatt, with plans to support MTIA generations through 2029. That figure describes a planned rollout, not capacity already operating.
Meta also uses Taiwan Semiconductor Manufacturing Co. to fabricate its processors, Reuters reported in March. The same report noted that Meta had signed agreements in February to buy tens of billions of dollars worth of chips from Nvidia and AMD. Meta describes its approach as matching different accelerators to different workloads, leaving a role for commercial chips alongside its own designs.
Making specialized hardware introduces a timing problem. Meta says chip development can take about two years, during which the AI workloads designers anticipated may change substantially. Its response is to use modular components and shorter development cycles. The MTIA 400, 450 and 500 share chassis, racks and networking infrastructure, according to the technical roadmap, so a new chip generation can fit into the same physical systems.
127K
2 posts, first seen 3h ago
Meta is advancing custom MTIA silicon, planning to deploy MTIA 450 (Arke) in H1 2027 and MTIA 500 (Astrid) by end-2027. These target efficient inference workloads with better performance-per-watt and cost than Nvidia systems. Meta partnered with Broadcom and TSMC.
Meta plans to deploy MTIA 450 in early 2027 and MTIA 500 during that year, aiming to lower the cost of running AI. Its expanded Broadcom partnership starts with a commitment exceeding 1 gigawatt. The chips are part of a mixed hardware strategy, and Meta says changing AI workloads can complicate designs years in development.
$META plans to deploy its new in house Arke chips in H1 2027 followed by next generation Astrid chips by year end. Meta says the chips will “save money and energy” as it builds more custom compute alongside its growing AI infrastructure.
The real $META rerating starts when Muse becomes the layer consumers use before they ever open apps like $AMZN, $UBER or $DASH Once the agent controls what gets searched, compared and ultimately bought then Meta starts owning the demand funnel itself and the business looks MUCH…
Meta plans to deploy two new generations of custom AI chips in 2027 as it tries to reduce the cost of running models across its services. Its roadmap, published March 11, schedules MTIA 450 for mass deployment in early 2027 and MTIA 500 during the same year.
Both prioritize inference, the work a trained model does when it responds to a request. Meta says designing around that workload can be more economical than using chips built primarily for large-scale model training. The goal is to make repeated AI use cheaper at the company's scale; the roadmap does not establish a guaranteed saving for each request.
The custom hardware also depends on outside partners. Meta's expanded agreement with Broadcom covers chip design, advanced packaging and networking. In its April 14 announcement, Broadcom said the initial commitment exceeds 1 gigawatt, with plans to support MTIA generations through 2029. That figure describes a planned rollout, not capacity already operating.
Meta also uses Taiwan Semiconductor Manufacturing Co. to fabricate its processors, Reuters reported in March. The same report noted that Meta had signed agreements in February to buy tens of billions of dollars worth of chips from Nvidia and AMD. Meta describes its approach as matching different accelerators to different workloads, leaving a role for commercial chips alongside its own designs.
Making specialized hardware introduces a timing problem. Meta says chip development can take about two years, during which the AI workloads designers anticipated may change substantially. Its response is to use modular components and shorter development cycles. The MTIA 400, 450 and 500 share chassis, racks and networking infrastructure, according to the technical roadmap, so a new chip generation can fit into the same physical systems.
Wall St Engine@wallstengine$META TO ROLL OUT TWO NEW IN-HOUSE AI CHIPS IN 2027, PLANS 1GW+ OF CUSTOM SILICON CAPACITY Meta plans to begin deploying its new MTIA 450 chip, code-named Arke, across data centers in the first half of 2027, as it pushes to reduce the cost and energy required to run AI models.…
Not enough discussion yet.
No sentiment analysis available yet.
Wall St Engine@wallstengine$META TO ROLL OUT TWO NEW IN-HOUSE AI CHIPS IN 2027, PLANS 1GW+ OF CUSTOM SILICON CAPACITY Meta plans to begin deploying its new MTIA 450 chip, code-named Arke, across data centers in the first half of 2027, as it pushes to reduce the cost and energy required to run AI models.…
Not enough discussion yet.
No sentiment analysis available yet.
#1
#1