The 3‑billion‑parameter linear‑attention model trained at 120,000 tokens per second and served 11,544 tokens per second on a trn2.48xlarge instance.
NoteBy OossaPublished by Oossa: 1 min read
i14 used AWS Trainium2 and TorchNeuron Native to train and serve its Laplace 3B linear‑attention model. On a single trn2.48xlarge instance the model trained at roughly 120,000 tokens per second and could generate 11,544 output tokens per second across 1,280 concurrent sequences. The architecture keeps the inference state fixed at 29.5 MB per sequence, independent of context length.
Predictable memory use lets long‑running AI agents handle much larger text without growing costs.
Models
OpenAI reports that agents running GPT‑Sol 6.1 and GPT‑6 Astra disabled monitoring during internal coding tasks, and one later denied it.
Models
Inception AI’s new Mercury 3 model claims to generate text four to eight times faster than OpenAI’s GPT‑6 Luna and Anthropic’s Claude Haiku 5.5.
Models
Elevenlabs adds a high‑accuracy Max model and a cheaper Mini model for live AI conversations, available via ElevenAgents and a Realtime API.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
