{"data":{"slug":"aws-inferentia2","etype":"chip","name":"AWS Inferentia2","cat":"AI Accelerator","subtitle":"Amazon's inference chip — cheap tokens for production serving.","summary":"Inferentia2 is the serving half of Annapurna Labs' silicon line: 32 GB of HBM per chip and a compiler stack (Neuron) that targets cost per inference rather than peak FLOPS. Inf2 instances gang up to 12 chips for large-model serving.","attrs":[{"g":"Overview","l":"Designer","v":"AWS (Annapurna Labs)"},{"g":"Overview","l":"GA","v":"April 2023"},{"b":"Vendor spec","g":"Memory","l":"Memory","v":"32 GB HBM per chip"},{"b":"Vendor spec","g":"Compute","l":"FP16/BF16","u":"TFLOPS","v":"190"},{"b":"Vendor spec","g":"Physical","l":"Scale","v":"up to 12 chips per Inf2 instance, NeuronLink interconnect"}],"kf":{"year":2023,"class":"AI Accelerator","memory":"32 GB HBM","designer":"AWS Annapurna"},"aliases":["Inferentia2","Inferentia","Inf2"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":"Shipping","region":null,"asof":"2026-01-15","sources":[{"url":"https://aws.amazon.com/ai/machine-learning/inferentia/","label":"AWS Inferentia page"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T11:47:54+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}