Axelera Unveils Titania Data Center AIPU Architecture for 2027

1 reports archived1 independent sourcesupdated 11/13/2026, 10:56:08

Synthesis & Latest Updates

1 Sources Cross-Validated

Dutch chip startup Axelera AI has disclosed the architecture of Titania, its third-generation AIPU targeting data center inference, with mass production slated for Q3 2027 and over $300 million in orders already booked. Optimized for sparse MoE models, the chip delivers 2.5 PFLOPS at FP8, and a single 4U eight-card server can run a 1.6T MoE model locally, with the company claiming 7x per-watt throughput versus current data center servers.

LATEST/Dutch chip startup Axelera AI has disclosed the architecture of Titania, its third-generation AIPU targeting data center inference, with mass production slated for Q3 2027 and over $300 million in orders already booked. Optimized for sparse MoE models, the chip delivers 2.5 PFLOPS at FP8, and a single 4U eight-card server can run a 1.6T MoE model locally, with the company claiming 7x per-watt throughput versus current data center servers.

Hourly heat curve

3 fully observed hours

Now

11.3

Peak

11.712:00

24h change

–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first

IT之家 · 智能时代T2Nov 13, 10:56·78 pts
Axelera Unveils Titania Data Center AIPU Architecture for 2027
- Titania uses a dual-chiplet D-IMC architecture with 2.5 PFLOPS FP8 compute, 128MB shared SRAM and 128GB LPDDR6 memory
- A single 4U eight-card air-cooled server can run a 1.6T sparse MoE model locally, with claimed 7x per-watt throughput over current servers
- Over $300 million in orders booked, but mass production is set for Q3 2027, leaving execution uncertainty
View Related Reports & Analysis Original Source