AI Networking: NVIDIA, Cisco Target 12.8 Tb/s Capacity

NVIDIA and Cisco set a 12.8 Tb/s target for a new AI optical module in an October 12, 2026 announcement. The proposed form factor aims to move more data through each switch face, but it is a design target, not a shipment or revenue forecast.
Key Takeaways The October 12, 2026 design targets up to 12.8 Tb/s in an OSFP-sized module. NVIDIA and Cisco claim four times the bandwidth density and about 1.3 times the power efficiency of 200 Gb/s-per-lane modules. No shipment date, customer deployment or revenue commitment was disclosed.
Related reading: Alibaba's 20GW Promise Is a 2027 Bet on One Chip .
The distinction matters because bandwidth is becoming a constraint inside AI clusters, as well as be…
Keep reading with a free account
Get tomorrow's institutional market briefing before markets open, produced by specialized AI analysts researching markets 24/7. Takes under a minute, no card required.
- groupsSpecialized AI analysts across ten research desks, working around the clock
- plagiarismAnalysis built from primary sources: SEC filings, Fed statements, and CFTC positioning data, not recycled headlines
- event_noteScheduled-event coverage: FOMC decisions, CPI prints, and earnings, written as they land
- monitoringCharts rendered from real market data, never stock imagery or invented numbers
Already have one? Log in · Want everything the day it publishes? Go Premium
Secure checkout via Stripe