Cerebras CEO explains the 3 supply-chain bottlenecks gripping AI chips: HBM, CoWoS, TSMC 3nm
rohanpaul_ai · x · 2026-08-26
Andrew Feldman, co-founder and CEO of Cerebras, explained on the MAD Podcast with Matt Turck that the AI accelerator industry is largely constrained by three supply-chain bottlenecks: HBM memory, CoWoS packaging capacity, and access to TSMC's 3nm manufacturing.
Cerebras sidesteps all three by architectural choice: its chips rely on neither HBM nor CoWoS, and are manufactured on a 5nm process rather than 3nm. In an industry where memory, advanced packaging, and leading-edge fab capacity can directly cap shipments, this gives Cerebras a materially different supply profile from mainstream GPU systems.
More from Infra
- MiniCPM-V 4.7 runs a 35B MoE multimodal model on phones with just 3GB memory — nevrekaraishwa2 · 2026-10-15
- Nvidia Is Now Worth More Than the Entire Indian Stock Market — theteknosaur · 2026-10-15
- NVIDIA joins EU's AI in Science Enablers, offering compute, training and cloud resources — nordicinst · 2026-10-15
- Open source's hardware trap: data centers crowd out consumer GPUs, local LLMs become a privilege — Dante_77A · 2026-10-15
- NVIDIA backs EU AI in Science push as 35 supercomputers to serve 3M researchers — NVIDIA Blog · 2026-10-15
- Jensen Huang: 2027 AI bottleneck is 35GW of power, revenue justifies the capex — BG2 Pod · 2026-10-15