Groq LPU
The deterministic inference engine famous for extreme tokens-per-second.
You're looking at a chip record: what this processor is, its key specs, who designs, manufactures and supplies its parts, and where it gets used.
Groq's Language Processing Unit strips out caches and dynamic scheduling: the compiler knows exactly where every byte is every cycle, using 230 MB of on-chip SRAM at 80 TB/s. Made on GlobalFoundries 14 nm — proof that architecture, not process node, drives its speed — LPU racks serve open models at hundreds to thousands of tokens per second. Founded by TPU creator Jonathan Ross; valued in the billions on 2024–25 raises with a major Saudi deployment deal.
Specifications & key facts
Each figure is labeled by basis: vendor spec, vendor claim, reported, estimate, or official. "Not publicly disclosed" means exactly that — we never invent values.
Overview
Manufacturing
Memory
Compute
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Designed by
Manufactured by
Competes with
Related
Sources
Record reviewed as of 2026-01-15 — see Methodology.